PATENTS   
Patents > Guidance, Tools, and Manuals >> Classification >>> Class Definition
    Class Numbers & Titles   | Class Numbers Only   | USPC Index   | International   | HELP  
You are viewing a Class definition.

 [Search a list of Patent Appplications for class 704]   CLASS 704,DATA PROCESSING: SPEECH SIGNAL PROCESSING, LINGUISTICS, LANGUAGE TRANSLATION, AND AUDIO COMPRESSION/DECOMPRESSION
Click here for a printable version of this file

SECTION I - CLASS DEFINITION

This is the generic class for apparatus and corresponding methods for constructing, analyzing, and modifying units of human language by data processing, in which there is a significant change in the data.

This class also provides for systems or methods that process speech signals for storage, transmission, recognition, or synthesis of speech.

This class also provides for systems or methods for bandwidth compression or expansion of an audio signal, or for time compression or expansion of an audio signal.

Class 704 is structured into three main divisions:

A. Linguistics.

B. Speech Signal Processing.

C. Audio Compression.

See Subclass References to the Current Class, below, for the subclasses located within each of these three main divisions.

SECTION II - LINES WITH OTHER CLASSES AND WITHIN THIS CLASS

A. LINGUISTICS

1. This class does not include subject matter wherein significant details of the modification or construction of documents are claimed. (See Class ?0? in the Search Class notes below in References to Other Classes, regarding Document Processing).

2. This class does not include subject matter directed to significant details of teaching languages. (See Class 434 in the Search Class notes in References to Other Classes, below).

3. This class does not include subject matter directed to significant details of the construction, analysis or modification of computer languages. (See Class 717 in the Search Class notes in References to Other Classes, below).

B. IMAGE ANALYSIS

1. This class does not include subject matter wherein significant image analysis is performed and speech signal processing is nominally claimed (see Class 382 in the Search Class notes in References to Other Classes, below).

2. This class includes subject matter directed to speech signal processing disclosed or claimed in plural diverse arts such as image analysis (classified, per se, in Class 382).

C. AUDIO SIGNAL PROCESSING

1. This class does not include subject matter wherein nominal bandwidth or time modifications are performed for other audio processing defined in Classes 381 or 84 (see Search Class notes below in References to Other Classes). Examples of subject matter not included are: Stereo, sound effects, hearing aids, input and output transducers, and musical instruments.

2. This class includes audio signal processing wherein significant processing is performed to modify the signal"s bandwidth or time characteristics for compression or expansion of the signal.

D. COMMUNICATIONS

1. This class does not include subject matter wherein significant details of a distinct communications system or telephone link is performed and speech signal processing is nominally claimed (see Classes 340, 370, 375, 379, 455 in the Search Class notes below in References to Other Classes.).

2. This class includes subject matter directed to speech signal processing disclosed or claimed in plural diverse arts such as various types of communication systems.

E. APPLICATIONS

1. This class does not include subject matter wherein significant details of application systems are performed and speech signal processing is nominally claimed.

2. This class includes subject matter directed to speech signal processing disclosed or claimed in plural diverse arts to include electrical and mechanical systems. Examples would include systems controlled by speech recognition, systems which create specific displays of speech data, systems for editing speech data and otherwise unrelated systems which incorporate speech signal processing details such as placing a speech synthesizer into novelty items.

SECTION III - SUBCLASS REFERENCES TO THE CURRENT CLASS

SEE OR SEARCH THIS CLASS, SUBCLASS:

1+,for linguistics.
100+,for speech signal processing.
500+,for audio compression.

SECTION IV - REFERENCES TO OTHER CLASSES

SEE OR SEARCH CLASS:

84Music,   subclasses 1+ for instruments used in producing music to include (a) electrical music instruments, (b) automatic instruments, and (c) hand-played instruments. Automatic and hand-played instruments are divided into four groups: stringed, wind, rigid vibrators, and membranes. This class also includes some accessory devices generally recognized as belonging to the art or industry.
181Acoustics,   various subclasses, for mechanically transmitting, amplifying and ascertaining the direction of sound and for mechanically muffling or filtering sound.
340Communications: Electrical,   subclasses 1.1 through 16.1for controlling one or more devices to obtain a plurality of results by transmission of a designated one of plural distinctive control signals over a smaller number of communication lines or channels.
341Coded Data Generation or Conversion,   various subclasses for electrical pulse and digit code converters (e.g., systems for originating or emitting a coded set of discrete signals or translating one code into another code wherein the meaning of the data remains the same but the formats may differ).
345Computer Graphics Processing and Selective Visual Display Systems,   various subclasses for the selective control of two or more light generating or light controlling display elements in accordance with a received image signal, and subclasses 1.1 through 3.4for visual display systems with selective electrical control including display memory organization and structure for storing image data and manipulating image data between a display memory and display device.
360Dynamic Magnetic Information Storage or Retrieval,   which is an integral part of Class 369 following subclass 18 , for record carriers and systems wherein information is stored and retrieved by interaction with a medium and there is relative motion between a medium and a transducer, for example, magnetic disk drive devices, and control thereof, per se.
365Static Information Storage and Retrieval,   various subclasses for addressable static singular storage elements or plural singular storage elements of the same type (i.e., the internal elements of memory, per se).
369Dynamic Information Storage or Retrieval,   various subclasses for record carriers and systems wherein information is stored and retrieved by interaction with a medium and there is relative motion between a medium and a transducer.
370Multiplex Communications,   for the simultaneous transmission of two or more signals over a common medium, particularly subclasses 58.1+ for time division multiplex (TDM) switching, subclasses 85.1+ for time division bus transmission, and subclasses 91+ for asynchronous TDM communications including addressing.
375Pulse or Digital Communications,   various subclasses for generic pulse or digital communication systems and synchronization of clocking signals from input data.
377Electrical Pulse Counters, Pulse Dividers, and Shift Registers: Circuits and Systems,   various subclasses for generic circuits for pulse counting.
379Telephonic Communications,   various subclasses for two-way electrical communication of intelligible audio information of arbitrary content over a link including an electrical conductor.
380Cryptography,   appropriate subclasses for cryptographic electric signal modification.
381Electrical Audio Signal Processing Systems and Devices,   various subclasses for wired one-way audio systems, per se.
382Image Analysis,   various subclasses for operations performed on image data with the aim of measuring a characteristic of an image, detecting variations, detecting structures, or transforming the image data, and for procedures for analyzing and categorizing patterns present in image data.
434Education and Demonstration,   subclasses 112+ for communication aids for the handicapped, subclasses 156+ for education and demonstration of language, subclasses 322+ for question or problem eliciting response.
455Telecommunications,   appropriate subclasses for modulated carrier wave communication, per se, and subclass 26.1 for subject matter which blocks access to a signal source or otherwise limits usage of modulated carrier equipment.
700Data Processing: Generic Control Systems or Specific Applications,   subclasses 1 through 89for data processing generic control systems, subclasses 90-306 for applications of computers in various environments.
702Data Processing: Measuring, Calibrating, or Testing,   appropriate subclasses for the application of computer data processing in measuring, calibrating, or testing.
708Electrical Computers: Arithmetic Processing and Calculating,   subclasses 1+ for hybrid computers, subclasses 100+ for calculators, digital signal processing and arithmetical processing, per se, subclasses 300+ for digital filters, and subclasses 800+ for electric analog computers.
713Electrical Computers and Digital Processing Systems: Support,   subclass 187 and 188 for software program protection or computer virus detection in combination with data encryption.
714Error Detection/Correction and Fault Detection/Recovery,   various subclasses for generic electrical pulse or pulse coded data error detection and correction.
715Data Processing: Presentation Processing of Document, Operator Interface Processing, and Screen Saver Display Processing,   subclasses 243 through 272for document processing including layout, editing, and spell-checking.
717Data Processing: Software Development, Installation, and Management,   appropriate subclasses for significant details of the construction, analysis, or modification of computer languages.

SECTION V - GLOSSARY

The terms below have been defined for purposes of classification in this class and are shown in underlined type when used in the class and subclass definitions. When these terms are not underlined in the definitions, the meaning is not restricted to the glossary definitions below.

CORRELATION

A statistical measurement of the interdependence or association between two variables that are quantitative or qualitative in nature. A typical calculation would be performed by multiplying a signal by either another signal (cross-correlation) or by a delayed version of itself (autocorrelation).

DISTANCE

A statistical measurement for comparing elements defined by variables or vectors using scalar or vector subtraction of those elements. Examples: distance=a-b, |a-b|, (a-b).5 or two vectors may be treated as objects such that the straight line distance is measured between them.

EXCITATION

Stimulation of the vocal tract by vibratory action of the vocal cords or by a turbulent air flow. In a digital system, the vocal tract is typically modelled with a filter and excitation of the filter is performed using time representations of pitch (voiced excitation) and noise (unvoiced excitation).

LANGUAGE

A systematic means of communicating ideas or feelings by the use of conventionalized sounds, gestures, or marks having understood meanings.

LINGUISTICS

The study of human speech including the units, nature, structure, and modification of language.

Masking

1. The interference with the perception of one sound (the signal) with another sound (the masker). 2. The number of decibels by which a masking sound will raise (or change) a listener"s threshold of audibility of other sounds.

Critical bandwidths

Bandwidths of the hearing process, as measured by the masking effect of a white, random noise in which a person detects a pure tone.

Bark spectrum

The width of one critical band.

Mel

A subjective measure of pitch based upon a signal of 1000 Hz. being defined as "1000 mels" where a perceived frequency twice as high is defined as 2000 mels and half as high as 500 mels.

NOISE

Any sound which is undesirable and interferes with one"s hearing or with a system"s analysis of desired sound.

Phon

The loudness level of any other sound based upon the SPL (sound pressure level measured in decibels) of a 1 kHz tone. For example, if we judge a certain waveform to sound as loud as a 1 kHz tone at 70 dB, then this waveform has a loudness level of 70 phons.

PITCH

The measurable frequency or period at which the glottis vibrates.

SIMILARITY

A statistical measurement which is inversely proportional to distance. For example, if two patterns are compared yielding a small distance, then the patterns would exhibit a large (or high degree of) similarity.

Sone

A measure of loudness as a function of frequency and sound pressure. A pure tone of 1 kHz. at 40 db above a normal listener"s threshold produces a loudness of 1 sone.

SPEECH

The communication or expression of thoughts in spoken words.

UNVOICED

Speech sounds produced by a turbulent flow of air created at some point of stricture in the vocal tract and usually lacking pitch.

VOICED

Speech sounds produced by vibratory action of the vocal cords and usually having pitch.

SUBCLASSES

[List of Patents for class 704 subclass 1]    1LINGUISTICS:
 This subclass is indented under the class definition.  Subject matter including means or steps for constructing a word, a phrase, or a sentence in a language.

SEE OR SEARCH CLASS:

434Education and Demonstration,   subclasses 156+ for demonstration and education in linguistics.
  
[List of Patents for class 704 subclass 2]    2Translation machine:
 This subclass is indented under subclass 1.  Subject matter wherein a language (i.e., source language) stored in a memory means is translated into another language (i.e., target language).

SEE OR SEARCH THIS CLASS, SUBCLASS:

9,for translation machines with significant natural language processing.

SEE OR SEARCH CLASS:

358Facsimile and Static Presentation Processing,   subclass 403 for document filing and retrieval system.
716Computer-Aided Design and Analysis of Circuits and Semiconductor Masks,   subclasses 103 through 105for translation of computer program in designing and analyzing circuits and semiconductor mask.
717Data Processing: Software Development, Installation, and Management,   subclasses 136 through 161for software program code translator or compiler in software development.
  
[List of Patents for class 704 subclass 3]    3Having particular Input/Output device:
 This subclass is indented under subclass 2.  Subject matter wherein the translation machine includes a means for reading into the memory means a language, for pronouncing the translated language or a particular user interface.
(1) Note. Examples of such devices include an optical scanner or voice synthesizer.
  
[List of Patents for class 704 subclass 4]    4Based on phrase, clause, or idiom:
 This subclass is indented under subclass 2.  Subject matter wherein the translation machine translates a series of words that form a syntactical unit.
  
[List of Patents for class 704 subclass 5]    5For partial translation:
 This subclass is indented under subclass 2.  Subject matter wherein the translation machine includes a means for providing translation for a specified portion of a sentence or a clause.
  
[List of Patents for class 704 subclass 6]    6Punctuation:
 This subclass is indented under subclass 2.  Subject matter wherein the translation machine translates a compound word formed by hyphenation or sentences with quotation marks, colons, semicolons, or parentheses.
  
[List of Patents for class 704 subclass 7]    7Storage or retrieval of data:
 This subclass is indented under subclass 2.  Subject matter including a means for assigning storage locations or accessing addresses to the memory means.

SEE OR SEARCH CLASS:

707Data Processing: Database, Data Mining,   and File Management or Data Structures subclasses 736 through 757for preparing data for information retrieval including clustering, generating an index, ranking, scoring and weighting records, latent semantic indexing, subclass 760 for translating queries between languages and 794 for semantic network data structures.
  
[List of Patents for class 704 subclass 8]    8Multilingual or national language support:
 This subclass is indented under subclass 1.  Subject matter including means or steps to adapt to, process, or support plural languages in systems or in software (i.e., providing language identifiers on files or providing screen prompts in a selected language), or to support the conventions or peculiarities of various national languages (i.e., alphabetical ordering, date or currency indications).

SEE OR SEARCH THIS CLASS, SUBCLASS:

200+,for details of translation between multiple languages.

SEE OR SEARCH CLASS:

715Data Processing: Presentation Processing of Document, Operator Interface Processing, and Screen Saver Display Processing,   subclasses 264 through 265for composing or editing multiple languages in a document and subclass 866 for customization or edition of operator interfaces.
  
[List of Patents for class 704 subclass 9]    9Natural language:
 This subclass is indented under subclass 1.  Subject matter includes a means for applying grammatical rules or other analyses (e.g., morphemic, syntax, semantic, etc.) to define the true meaning of a sentence or phrase.
(1) Note. When words are undefined in the dictionary of a natural language, the grammatical rules or other analyses are applied in order to determine the true meaning of a sentence or a phrase.

SEE OR SEARCH CLASS:

707Data Processing: Database, Data Mining, and File Management or Data Structures,   subclasses 736 through 757for preparing data for information retrieval including clustering, generating an index, ranking, scoring and weighting records, latent semantic indexing, subclass 760 for translating queries between languages and 794 for semantic network data structures.
  
[List of Patents for class 704 subclass 10]    10Dictionary building, modification, or prioritization:
 This subclass is indented under subclass 1.  Subject matter including a construction, a change, or an orderly arrangement of dictionary, thesauri, or the like.

SEE OR SEARCH THIS CLASS, SUBCLASS:

9,for mere use in natural language processing.
200+,for mere use in translation.

SEE OR SEARCH CLASS:

707Data Processing: Database, Data Mining, and File Management or Data Structures,   subclasses 736 through 757for preparing data for information retrieval including clustering, generating an index, ranking, scoring, weighting records and database details of dictionaries.
715Data Processing: Presentation Processing of Document, Operator Interface Processing, and Screen Saver Display Processing,   subclasses 259 through 260for mere use of a dictionary in editing or composition of a document.
  
[List of Patents for class 704 subclass 200]    200SPEECH SIGNAL PROCESSING:
 This subclass is indented under the class definition.  Subject matter wherein the system performs operations or functions on signals which represent speech.

SEE OR SEARCH THIS CLASS, SUBCLASS:

500+,for audio (other than speech) signal bandwidth compression or expansion.

SEE OR SEARCH CLASS:

379Telephonic Communications,   appropriate subclasses for speech signal processing in a telephone system or device.
  
[List of Patents for class 704 subclass 200.1]    200.1Psychoacoustic
 This subclass is indented under subclass 200.  Subject matter wherein an operation on the signal is based upon the masking behavior of the human auditory system.
(1) Note. The calculation of masking thresholds based upon incoming analysis of audio is the basis of psychoacoustic compression because the frequency with the highest local amplitude will tend to mask (make inaudible) nearby frequencies below the threshold.
(2) Note. MPEG (Motion Picture Experts Group) sets international standards such as MPEG 1, level 3 (commonly called MP3) for psychoacoustic coding to achieve audio compression of up to 10:1. Typical coders work on a 16-bit PCM audio signal, which is the typical CD quality standard.
(3) Note. Only white noise in a bandwidth centered about a tone and less than or equal to the critical bandwidth contributes to the masking effect. Critical bands are generally considered a set of filters or channels tuned to different center frequencies having a bandwidth of less than a third of an octave.
(4) Note. A plot of frequency versus pitch in mels is similar in shape to the plot of frequency versus the position of auditory-nerve patches on the basilar membrane. This is evidence that human judgment of pitch is based upon the point of excitation along the basilar membrane in the ear.

SEE OR SEARCH CLASS:

382Image Analysis,   subclass 239 for adaptive coding used in MPEG, JPEG & motion JPEG images.
  
[List of Patents for class 704 subclass 201]    201For storage or transmission:
 This subclass is indented under subclass 200.  Subject matter wherein the speech, which may be in coded or reduced formats, is stored or transmitted.
  
[List of Patents for class 704 subclass 202]    202Neural networks:
 This subclass is indented under subclass 201.  Subject matter wherein coding is performed using parallel distributed processing elements constructed in hardware or simulated in software.

SEE OR SEARCH THIS CLASS, SUBCLASS:

259,for neural networks which decode a coded speech signal.
  
[List of Patents for class 704 subclass 203]    203Transformations:
 This subclass is indented under subclass 201.  Subject matter wherein the speech is encoded using a specific mathematical function (e.g., Fourier, Walsh, cosine/sine transform, etc.).
  
[List of Patents for class 704 subclass 204]    204Orthogonal functions:
 This subclass is indented under subclass 203.  Subject matter wherein the function is orthogonal (transformations as applied to vector, matrix, linear and polynomial functions, for example).
  
[List of Patents for class 704 subclass 205]    205Frequency:
 This subclass is indented under subclass 201.  Subject matter wherein the speech is represented by frequency.
  
[List of Patents for class 704 subclass 206]    206Specialized information:
 This subclass is indented under subclass 205.  Subject matter wherein the frequency data is analyzed to identify specific speech information.
  
[List of Patents for class 704 subclass 207]    207Pitch:
 This subclass is indented under subclass 206.  Subject matter wherein the specific speech information represents the predominant frequency of the speech.
  
[List of Patents for class 704 subclass 208]    208Voiced or unvoiced:
 This subclass is indented under subclass 207.  Subject matter wherein the specific speech information represents the presence (voiced) or absence (unvoiced) of predominant frequency components.
  
[List of Patents for class 704 subclass 209]    209Formant:
 This subclass is indented under subclass 206.  Subject matter wherein the specific speech information represents the frequency values of any of several resonance bands which determine the phonetic quality of a vowel sound.
  
[List of Patents for class 704 subclass 210]    210Silence decision:
 This subclass is indented under subclass 206.  Subject matter wherein the specific speech information represent the presence or absence of speech.
  
[List of Patents for class 704 subclass 211]    211Time:
 This subclass is indented under subclass 201.  Subject matter wherein the speech signal is represented using time (e.g., time measurements and energy measured over time).
  
[List of Patents for class 704 subclass 212]    212Pulse code modulation (PCM):
 This subclass is indented under subclass 211.  Subject matter wherein the signal is sampled over time, and the magnitude of each sample is quantized and converted into a digital signal.
  
[List of Patents for class 704 subclass 213]    213Zero crossing:
 This subclass is indented under subclass 211.  Subject matter wherein the zero crossings of the signal are used to measure time or frequency.
  
[List of Patents for class 704 subclass 214]    214Voiced or unvoiced:
 This subclass is indented under subclass 211.  Subject matter wherein time measurements are used to determine the presence (voiced) or absence (unvoiced) of predominant frequency components.
  
[List of Patents for class 704 subclass 215]    215Silence decision:
 This subclass is indented under subclass 211.  Subject matter wherein time measurements are used to determine the presence or absence of speech (e.g., pauses between words, etc.).
  
[List of Patents for class 704 subclass 216]    216Correlation function:
 This subclass is indented under subclass 211.  Subject matter wherein analysis of speech is performed using relationships between time series samples.
  
[List of Patents for class 704 subclass 217]    217Autocorrelation:
 This subclass is indented under subclass 216.  Subject matter wherein the relationships are between different speech samples taken from the same time series.
  
[List of Patents for class 704 subclass 218]    218Cross-correlation:
 This subclass is indented under subclass 216.  Subject matter wherein the relationships are between speech samples taken from different time series.
  
[List of Patents for class 704 subclass 219]    219Linear prediction:
 This subclass is indented under subclass 201.  Subject matter wherein input samples of speech are estimated from past samples of an input sequence.
  
[List of Patents for class 704 subclass 220]    220Analysis by synthesis:
 This subclass is indented under subclass 201.  Subject matter wherein the speech signal is coded and corrected by the difference of the decoded coded signal from the original speech signal.
  
[List of Patents for class 704 subclass 221]    221Pattern matching vocoders:
 This subclass is indented under subclass 201.  Subject matter wherein speech signals are compared and matching patterns are encoded.
  
[List of Patents for class 704 subclass 222]    222Vector quantization:
 This subclass is indented under subclass 221.  Subject matter wherein the encoding maps a sequence of continuous or discrete vectors into a digital sequence.
  
[List of Patents for class 704 subclass 223]    223Excitation patterns:
 This subclass is indented under subclass 221.  Subject matter wherein the encoding models speech using representations including the primary frequency period or periods (e.g., pitchexcitation, multipulse excitation, etc.).
  
[List of Patents for class 704 subclass 224]    224Normalizing:
 This subclass is indented under subclass 201.  Subject matter wherein modifications of the speech signal emphasize or deemphasize certain features (e.g., spectral slope, average power, etc.).
  
[List of Patents for class 704 subclass 225]    225Gain control:
 This subclass is indented under subclass 201.  Subject matter wherein the speech is adjusted to maintain an average amplitude.
  
[List of Patents for class 704 subclass 226]    226Noise:
 This subclass is indented under subclass 201.  Subject matter wherein the coding reduces the effects of undesired signal components.
  
[List of Patents for class 704 subclass 227]    227Pre-transmission:
 This subclass is indented under subclass 226.  Subject matter wherein the coding precedes transmission.
  
[List of Patents for class 704 subclass 228]    228Post-transmission:
 This subclass is indented under subclass 226.  Subject matter wherein decoding after transmission minimizes the effects of noise in the transmission path.
  
[List of Patents for class 704 subclass 229]    229Adaptive bit allocation:
 This subclass is indented under subclass 201.  Subject matter wherein limited storage or transmission resources are allocated by giving more resources to areas containing more data and giving fewer resources to areas containing less data.
  
[List of Patents for class 704 subclass 230]    230Quantization:
 Subject matter under 201 wherein coded information is mapped into digital words described by binary symbols.
  
[List of Patents for class 704 subclass 231]    231Recognition:
 This subclass is indented under subclass 200.  Subject matter wherein speech is separated into discrete components which are distinguished from one another.
  
[List of Patents for class 704 subclass 232]    232Neural networks:
 This subclass is indented under subclass 231.  Subject matter using parallel distributed processing elements constructed in hardware or simulated in software.
  
[List of Patents for class 704 subclass 233]    233Detect speech in noise:
 This subclass is indented under subclass 231.  Subject matter wherein the discrete components are distinguished from noise.
  
[List of Patents for class 704 subclass 234]    234Normalizing:
 This subclass is indented under subclass 231.  Subject matter wherein the discrete components are modified to emphasize or deemphasize certain features (e.g., spectral slope, average power, etc.).
  
[List of Patents for class 704 subclass 235]    235Speech to image:
 This subclass is indented under subclass 231.  Subject matter wherein the distinguished discrete components are converted into image output (e.g., text).
  
[List of Patents for class 704 subclass 236]    236Specialized equations or comparisons:
 This subclass is indented under subclass 231.  Subject matter wherein the discrete components are distinguished using specific mathematical functions.
  
[List of Patents for class 704 subclass 237]    237Correlation:
 This subclass is indented under subclass 236.  Subject matter wherein the specific function measures a correlation between discrete components (e.g., absolute magnitude difference functions (AMDF), autocorrelation, cross-correlation, etc.).
  
[List of Patents for class 704 subclass 238]    238Distance:
 This subclass is indented under subclass 236.  Subject matter wherein the specific function measures the difference between discrete components.
  
[List of Patents for class 704 subclass 239]    239Similarity:
 This subclass is indented under subclass 236.  Subject matter wherein the specific function measures the similarity between discrete components.
  
[List of Patents for class 704 subclass 240]    240Probability:
 This subclass is indented under subclass 236.  Subject matter wherein the specific function uses probability to determine the occurrence of a discrete component.
  
[List of Patents for class 704 subclass 241]    241Dynamic time warping:
 This subclass is indented under subclass 236.  Subject matter wherein time components of the discrete components are aligned with reference components (e.g., using dynamic programming).
  
[List of Patents for class 704 subclass 242]    242Viterbi Trellis:
 This subclass is indented under subclass 236.  Subject matter wherein discrete components are distinguished by traversing possible paths through a time series.
  
[List of Patents for class 704 subclass 243]    243Creating patterns for matching:
 This subclass is indented under subclass 231.  Subject matter including specific methods for registering the discrete components to be used as references.
  
[List of Patents for class 704 subclass 244]    244Update patterns:
 This subclass is indented under subclass 243.  Subject matter wherein the references are modified to improve recognition (e.g., learning).
  
[List of Patents for class 704 subclass 245]    245Clustering:
 This subclass is indented under subclass 243.  Subject matter wherein similar references are placed or divided into groups (e.g., K-means algorithm, nearest neighbor, etc.).
  
[List of Patents for class 704 subclass 246]    246Voice recognition:
 This subclass is indented under subclass 231.  Subject matter wherein different voices are distinguished (e.g., speaker identification or verification).
  
[List of Patents for class 704 subclass 247]    247Preliminary matching:
 This subclass is indented under subclass 246.  Subject matter using an initial comparison followed by a more detailed recognition.
  
[List of Patents for class 704 subclass 248]    248Endpoint detection:
 This subclass is indented under subclass 246.  Subject matter including the identification of the beginning and ending points of speech sound segments.
  
[List of Patents for class 704 subclass 249]    249Subportions:
 This subclass is indented under subclass 246.  Subject matter including separating speech into sound segments (e.g., utterances, words, phonemes, allophones, etc.).
  
[List of Patents for class 704 subclass 250]    250Specialized models:
 This subclass is indented under subclass 246.  Subject matter including models which describe the interconnections between speech sound segments.
  
[List of Patents for class 704 subclass 251]    251Word recognition:
 This subclass is indented under subclass 231.  Subject matter wherein different words are distinguished (i.e., the meaning of what is spoken).
  
[List of Patents for class 704 subclass 252]    252Preliminary matching:
 This subclass is indented under subclass 251.  Subject matter using an initial comparison followed by a more detailed recognition.
  
[List of Patents for class 704 subclass 253]    253Endpoint detection:
 This subclass is indented under subclass 251.  Subject matter identifying the beginning and ending points of words.
  
[List of Patents for class 704 subclass 254]    254Subportions:
 This subclass is indented under subclass 251.  Subject matter identifying speech sound segments (e.g., phonemes, allophones, etc.).
  
[List of Patents for class 704 subclass 255]    255Specialized models:
 This subclass is indented under subclass 251.  Subject matter including models which describe the interconnections between words or subportions of words.
  
[List of Patents for class 704 subclass 256]    256Markov:
 This subclass is indented under subclass 255.  Subject matter wherein the models include states which represent speech sound portions and transitions which represent connections between speech sound portions (e.g., hidden Markov models, heuristic Markov models, etc.).
  
[List of Patents for class 704 subclass 256.1]    256.1Hidden Markov Model (HMM):
 This subclass is indented under subclass 256.  Subject matter wherein a Markov chain used in the recognition process has un-observable (hidden) states.
(1) Note. The subject matter in this subclass is substantially the same in scope as ECLA (G10L 15/14M).
(2) Note. The observation model itself is part of the stochastic process (Markov Chain) with an underlying stochastic process that is not directly observable, but can be observed through a set of stochastic processes that produce the sequence of observations.
(3) Note. The HMM has different elements, including the following – number of states, the number of distinct observations per state, state transition probability distribution, the observation symbol probability distribution, and the initial state distribution.
(4) Note. The manipulation of HMM s can be use in improving the probability of observation sequences, optimizing state sequences, or maximizing the probability of the state sequences.
(5) Note. Subcategories to the types of HMM s include finite state, discrete versus continuous, mixture densities, autoregressive, null transition, tied states, and state duration.
  
[List of Patents for class 704 subclass 256.2]    256.2Training of HMM:
 This subclass is indented under subclass 256.1.  Subject matter wherein the models include a learning process for recognizing speech data, e.g., the construction of a library of models for the words in a vocabulary, including the states.
(1) Note. The subject matter in this subclass is substantially the same in scope as ECLA (G10L 15/14M1).
  
[List of Patents for class 704 subclass 256.3]    256.3With insufficient amount of training data, e.g., state sharing, tying, and deleted interpolation:
 This subclass is indented under subclass 256.2.  Subject matter wherein intrinsic parameters of the HMM are modified to overcome lack of training data, and to simplify the model, e.g., state sharing, tying, and deleted interpolation.
(1) Note. The subject matter in this subclass is substantially the same in scope as ECLA (G10L 15/14M1S).
(2) Note. State sharing involves combining two or more separately trained models, one of which is more reliably trained than the other. The scenario in which this can happen is the case when we use tied states which forces "different" states to share an identical statistical characterization, effectively reducing the number of parameters in the model.
(3) Note. Parameter tying involves setting up an equivalence relation between HMM parameters in different states. In this manner the number of independent parameters in the model is reduced and the parameter estimation becomes somewhat simpler and in some cases more reliable. Parameter tying is used when the observation density, for example, is known to be the same in two or more states.
(4) Note. Deleted interpolation is a parameter method aimed to improve model reliability. The concept involves combining two or more separately trained models, one of which is more reliably trained than the other. The scenario in which this can happen is the case when we use tied states which forces "different" states to share an identical statistical characterization, effectively reducing the number of parameters in the model. The technique of deleted interpolation has been successfully applied to a number of problems in speech recognition, including the estimation of trigram word probabilities for language models, and the estimation of HMM output probabilities for trigram phone models.
  
[List of Patents for class 704 subclass 256.4]    256.4Duration modeling in HMM, e.g., semi HMM, segmental models, transition probabilities:
 This subclass is indented under subclass 256.1.  Subject matter wherein the HMM includes a duration state model for speech recognition, e.g., semi HMM’s segmental models, and transition probabilities.
(1) Note. The subject matter in this subclass is substantially the same in scope as ECLA (G10L 15/14M2).
(2) Note. A semi- Markov HMM is like an HMM except each state can emit a sequence of observations.
(3) Note. Within a state segment models introduce dependency between frames via their common dependence on a trajectory. There may be only a single trajectory or a continuous mixture of trajectories. The probability distribution over the sequence of frames for a state, given the duration and trajectory, is then typically modeled as independent Gaussian distributions for each time step, centered on the trajectory.
(4) Note. Symbol emission probabilities are associated to the states and transition probabilities to the connections between them.
  
[List of Patents for class 704 subclass 256.5]    256.5Hidden Markov (HM) Network:
 This subclass is indented under subclass 256.1.  Subject matter including a HMM structure wherein subgroups of HMM types are used to perform speech recognition.
(1) Note. The subject matter in this subclass is substantially the same in scope as ECLA (G10L 15/14M3).
(2) Note. Each subgroup can vary by type of model, model size, and observation symbols.
  
[List of Patents for class 704 subclass 256.6]    256.6State Emission Probability:
 This subclass is indented under subclass 256.1.  Subject matter wherein the HMM contains probability density function such that an emission probability is calculated for each state within the model.
(1) Note. The subject matter in this subclass is substantially the same in scope as ECLA (G10L 15/14M4).
(2) Note. For each state j, and for each possible output, a probability that a particular output symbol o is observed in that state. This is represented by the function bj(o), which gives the probability that o is emitted in state j. This is called the emission probability.
  
[List of Patents for class 704 subclass 256.7]    256.7Continuous density, e.g., Gaussian distribution, Laplace:
 This subclass is indented under subclass 256.6.  Subject matter wherein the HMM contains continuous probability density observation models for the purpose of avoiding possible signal degradation inherent with discrete representations of signals.
(1) Note. The subject matter in this subclass is substantially the same in scope as ECLA (G10L 15/14M4C).
  
[List of Patents for class 704 subclass 256.8]    256.8Discrete density, e.g., Vector Quantization preprocessor, look up tables:
 This subclass is indented under subclass 256.6.  Subject matter wherein the HMM contains discrete probability density observation models which allows for the use of a discrete probability density within each state of the model.
(1) Note. The subject matter in this subclass is substantially the same in scope as ECLA (G10L 15/14M4D).
(2) Note. Discrete probability density is used when the state of the model is discrete (e.g. representing a letter of the alphabet). Vector quantization is used to model its state.
  
[List of Patents for class 704 subclass 257]    257Natural language:
 This subclass is indented under subclass 255.  Subject matter wherein the models include grammatical constraints (e.g., syntax, etc.).
  
[List of Patents for class 704 subclass 258]    258Synthesis:
 This subclass is indented under subclass 200.  Subject matter wherein component parts of a speech signal are combined to produce a synthetic speech output.
  
[List of Patents for class 704 subclass 259]    259Neural networks:
 This subclass is indented under subclass 258.  Subject matter wherein synthetic speech output is formed using parallel distributed processing elements constructed in hardware or simulated in software.
  
[List of Patents for class 704 subclass 260]    260Image to speech:
 This subclass is indented under subclass 258.  Subject matter wherein the component parts are related to image data (e.g., text to speech, etc.).
  
[List of Patents for class 704 subclass 261]    261Vocal tract model:
 This subclass is indented under subclass 258.  Subject matter wherein the component parts model a human vocal tract.
  
[List of Patents for class 704 subclass 262]    262Linear prediction:
 This subclass is indented under subclass 258.  Subject matter wherein the component parts are represented by coefficients derived from a sequence of past speech samples.
  
[List of Patents for class 704 subclass 263]    263Correlation:
 This subclass is indented under subclass 258.  Subject matter wherein the component parts are represented by coefficients derived from relationships between time series speech samples.
  
[List of Patents for class 704 subclass 264]    264Excitation:
 This subclass is indented under subclass 258.  Subject matter wherein the component parts are represented by the period of the primary frequency of the speech signal (e.g., pitchexcitation, multi-pulse excitation, etc.).
  
[List of Patents for class 704 subclass 265]    265Interpolation:
 This subclass is indented under subclass 258.  Subject matter wherein the component parts are combined using estimates of intermediate values (e.g., waveform smoothing).
  
[List of Patents for class 704 subclass 266]    266Specialized model:
 This subclass is indented under subclass 258.  Subject matter wherein the component parts are combined or linked together in a defined manner (e.g., Markov models, trees, tries (tables representing trees), graphs, etc.).
  
[List of Patents for class 704 subclass 267]    267Time element:
 This subclass is indented under subclass 258.  Subject matter wherein the component parts comprise time based elements (e.g., words, phonemes, allophones, etc.).
  
[List of Patents for class 704 subclass 268]    268Frequency element:
 This subclass is indented under subclass 258.  Subject matter wherein the component parts comprise frequency based elements (e.g., pitch variations, inflection, formants, etc.).
  
[List of Patents for class 704 subclass 269]    269Transformation:
 This subclass is indented under subclass 258.  Subject matter wherein the component parts are restored to speech using specific mathematical functions (e.g., Fourier, Walsh, Hilbert, Z-transform, cosine/sine transforms, etc.).
  
[List of Patents for class 704 subclass 270]    270Application:
 This subclass is indented under subclass 200.  Subject matter intended or designed for a specified use to which the speech signal processing is being applied.
  
[List of Patents for class 704 subclass 270.1]    270.1Speech assisted network
 This subclass is indented under subclass 270.  Subject matter wherein a system that employs speech recognition or synthesis to control or to provide user feedback such that the processing of speech data may occur at various levels within a computer network.
(1) Note. Various levels of processing would include local or remote locations relative to the user in order to make use of available resources. For example, a local terminal might not have the necessary storage or processing power but this can be overcome by accessing resources over a network. Such resources may include the raw processing power necessary for analysis and pattern matching as well as dictionaries having data relevant to large vocabularies and multiple languages.
(2) Note. Nominal recitations of speech or audio in network applications are classified elsewhere.

SEE OR SEARCH CLASS:

348Television,   subclasses 13 through 20for 2-way interactive conferencing.
370Multiplex Communications,   subclasses 229 through 240for data flow congestion prevention or control, subclasses 260-269 for conferencing and subclass 351 for voice over internet.
375Pulse or Digital Communications,   subclasses 354 and 356 for synchronizing data for streaming over the internet.
707Data Processing: Database, Data Mining, and File Management or Data Structures,   subclasses 770 , 966 through 974 and 999.010 for distributed databases searching and access.
709Electrical Computers and Digital processing systems: Multiple computer or Process Coordinating,   subclasses 227 through 229for network computer-to-computer connections.
715Data Processing: Presentation Processing of Document, Operator Interface Processing, and Screen Saver Display Processing,   subclasses 234 through 242for HTML, SGML documents.
  
[List of Patents for class 704 subclass 271]    271Handicap aid:
 This subclass is indented under subclass 270.  Subject matter for assisting handicapped people (e.g., blind or speech impaired communication and control).
  
[List of Patents for class 704 subclass 272]    272Novelty item:
 This subclass is indented under subclass 270.  Subject matter for novelty items (e.g., greeting cards, toys, etc.).
  
[List of Patents for class 704 subclass 273]    273Security system:
 This subclass is indented under subclass 270.  Subject matter for providing security (e.g., limited access).

SEE OR SEARCH CLASS:

726Information Security,   subclasses 1 through 36for information security in computers or digital processing system.
  
[List of Patents for class 704 subclass 274]    274Warning/alarm system:
 This subclass is indented under subclass 270.  Subject matter for providing an audible warning or alarm (e.g., multiple sensors, car gauges, etc.).
  
[List of Patents for class 704 subclass 275]    275Speech controlled system:
 This subclass is indented under subclass 270.  Subject matter for controlling specific devices through speech or voice commands.
  
[List of Patents for class 704 subclass 276]    276Pattern display:
 This subclass is indented under subclass 270.  Subject matter for providing visual output representing speech (e.g., computer displays of speech data).
  
[List of Patents for class 704 subclass 277]    277Translation:
 This subclass is indented under subclass 270.  Subject matter for translating one language into another language.
  
[List of Patents for class 704 subclass 278]    278Sound editing:
 This subclass is indented under subclass 270.  Subject matter wherein speech is edited using waveform portions or other representations of the sounds to be modified.
  
[List of Patents for class 704 subclass 500]    500AUDIO SIGNAL BANDWIDTH COMPRESSION OR EXPANSION:
 This subclass is indented under the class definition.  Subject matter where there is either an expansion or reduction of the bandwidth required for transmission of a sound signal.
(1) Note. This subclass and its indents provide for bandwidth compression or expansion of audio signals other than speech signals.

SEE OR SEARCH THIS CLASS, SUBCLASS:

200+,for expansion or reduction of a speech signal"s bandwidth.
503+,for time compression or expansion of audio signals.

SEE OR SEARCH CLASS:

333Wave Transmission Lines and Networks,   subclass 14 for amplitude compression and expansion in a long transmission line.
348Television,   subclasses 384.1 through 440.1for bandwidth reduction of an analog television signal.
358Facsimile and Static Presentation Processing,   subclasses 426.01 through 426.16for bandwidth reduction of a facsimile signal.
360Dynamic Magnetic Information Storage or Retrieval,   subclasses 8+ for the use of a magnetic recorder to alter the bandwidth of a signal.
369Dynamic Information Storage or Retrieval,   subclass 60.01 for the use of a dynamic storage device to change the bandwidth of a signal.
370Multiplex Communications,   subclass 118 for bandwidth compression in a multiplex system.
375Pulse or Digital Communications,   subclasses 240 through 241for bandwidth compression or expansion of a pulse or digital signal, particularly subclasses 240.01-240.29 for digital television.
381Electrical Audio Signal Processing Systems and Devices,   subclass 106 for amplitude compression or expansion.
455Telecommunications,   subclass 72 for message signal compression or expansion in an analog signal modulated carrier wave communication system.
  
[List of Patents for class 704 subclass 501]    501With content reduction encoding:
 This subclass is indented under subclass 500.  Subject matter combined with means to discard and replace redundant information by a code indicating what has been discarded.

SEE OR SEARCH CLASS:

341Coded Data Generation or Conversion,   subclass 55 for content reduction encoding, per se.
  
[List of Patents for class 704 subclass 502]    502Delay line:
 This subclass is indented under subclass 500.  Subject matter having means to cause a time delay of a sound signal.

SEE OR SEARCH CLASS:

333Wave Transmission Lines and Networks,   subclasses 138 through 165for delay lines, per se.
  
[List of Patents for class 704 subclass 503]    503AUDIO SIGNAL TIME COMPRESSION OR EXPANSION (E.G., RUN LENGTH CODING):
 This subclass is indented under the class definition.  Subject matter where there is either an expansion or reduction of the time required for transmission of a nonspeech sound signal.

SEE OR SEARCH THIS CLASS, SUBCLASS:

211+,for expansion or reduction of the time required for transmission of a speech signal.
500+,for frequency compression or expansion of a nonspeech audio signal.

SEE OR SEARCH CLASS:

358Facsimile and Static Presentation Processing,   subclasses 426.01 through 426.16for time compression of a facsimile signal.
360Dynamic Magnetic Information Storage or Retrieval,   subclasses 8+ for the use of a magnetic recorder to alter the time duration of a recorded signal.
369Dynamic Information Storage or Retrieval,   subclass 60.01 for the use of a dynamic storage device to alter the time duration of a recorded signal.
370Multiplex Communications,   subclass 109 for time compression or expansion in a time division multiplex system.
381Electrical Audio Signal Processing Systems and Devices,   subclass 106 for amplitude compression or expansion.
455Telecommunications,   subclass 72 for message signal compression or expansion in an analog signal modulated carrier wave communication system.
  
[List of Patents for class 704 subclass 504]    504With content reduction encoding
 This subclass is indented under subclass 503.  Subject matter combined with means to discard and replace redundant information by a code indicating what has been discarded.

SEE OR SEARCH CLASS:

341Coded Data Generation or Conversion,   subclass 55 for content reduction encoding, per se.
  

E-SUBCLASSES

NOTE—E-subclasses in USPC Class 704/E17.001-E13.014 were created as duplicates of EPO groups in the entire subclass G10L. With the implementation of CPC, these E-subclasses should no longer be used. Instead, use CPC groups in the entire subclass G10L.

The E-subclasses in U.S. Class 704 provide for methods and devices for analyzing or synthesizing spoken language and for detecting, recognizing, or modifying speech signal characteristics.

[List of Patents for class 704 subclass E11.001]    E11.001MISCELLANEOUS ANALYSIS OR DETECTION OF SPEECH CHARACTERISTICS:
 This main group provides for processes and apparatus for analyzing or detecting speech characteristics not provided for elsewhere. This subclass is substantially the same in scope as ECLA classification G10L11/00.
  
[List of Patents for class 704 subclass E11.002]    E11.002General speech analysis without concrete application:
 This subclass is indented under subclass E11.001. This subclass is substantially the same in scope as ECLA classification G10L11/00A.
  
[List of Patents for class 704 subclass E11.003]    E11.003Detection of presence or absence of speech signals:
 This subclass is indented under subclass E11.001. This subclass is substantially the same in scope as ECLA classification G10L11/02.
  
[List of Patents for class 704 subclass E11.004]    E11.004Voice/data decision:
 This subclass is indented under subclass E11.003. This subclass is substantially the same in scope as ECLA classification G10L11/02D.
  
[List of Patents for class 704 subclass E11.005]    E11.005End point detection:
 This subclass is indented under subclass E11.003. This subclass is substantially the same in scope as ECLA classification G10L11/02E.
  
[List of Patents for class 704 subclass E11.006]    E11.006Pitch determination of speech signals:
 This subclass is indented under subclass E11.001. This subclass is substantially the same in scope as ECLA classification G10L11/04.
  
[List of Patents for class 704 subclass E11.007]    E11.007Voiced-unvoiced decision:
 This subclass is indented under subclass E11.001. This subclass is substantially the same in scope as ECLA classification G10L11/06.
  
[List of Patents for class 704 subclass E13.001]    E13.001SPEECH SYNTHESIS; TEXT TO SPEECH SYSTEMS:
 This main group provides for processes and apparatus for synthesizing speech. This subclass is substantially the same in scope as ECLA classification G10L13/00.
  
[List of Patents for class 704 subclass E13.002]    E13.002Methods for producing synthetic speech; speech synthesizers:
 This subclass is indented under subclass E13.001. This subclass is substantially the same in scope as ECLA classification G10L13/02.
  
[List of Patents for class 704 subclass E13.003]    E13.003Concept-to-speech synthesizers; generation of natural phrases not from text but from machine-based concepts:
 This subclass is indented under subclass E13.002. This subclass is substantially the same in scope as ECLA classification G10L13/02C.
  
[List of Patents for class 704 subclass E13.004]    E13.004Sound editing, manipulating voice of the synthesizer:
 This subclass is indented under subclass E13.002. This subclass is substantially the same in scope as ECLA classification G10L13/02E.
  
[List of Patents for class 704 subclass E13.005]    E13.005Details of speech synthesis systems, e.g., synthesizer architecture, memory management, etc.:
 This subclass is indented under subclass E13.001. This subclass is substantially the same in scope as ECLA classification G10L13/04.
  
[List of Patents for class 704 subclass E13.006]    E13.006Architecture of speech synthesizers:
 This subclass is indented under subclass E13.005. This subclass is substantially the same in scope as ECLA classification G10L13/04A.
  
[List of Patents for class 704 subclass E13.007]    E13.007Excitation:
 This subclass is in dented under subclass E13.005. This subclass is substantially the same in scope as ECLA classification G10L13/04E.
  
[List of Patents for class 704 subclass E13.008]    E13.008Systems using speech synthesizers:
 This subclass is indented under subclass E13.005. This subclass is substantially the same in scope as ECLA classification G10L13/04U.
  
[List of Patents for class 704 subclass E13.009]    E13.009Elementary speech units used in speech synthesizers; concatenation rules:
 This subclass is indented under subclass E13.001. This subclass is substantially the same in scope as ECLA classification G10L13/06.
  
[List of Patents for class 704 subclass E13.01]    E13.01Concatenation:
 This subclass is indented under subclass E13.009. This subclass is substantially the same in scope as ECLA classification G10L13/06C.
  
[List of Patents for class 704 subclass E13.011]    E13.011Text analysis, generation of parameters for speech synthesis out of text, e.g., grapheme to phoneme translation, prosody generation, stress, or intonation determination, etc.:
 This subclass is indented under subclass E13.001. This subclass is substantially the same in scope as ECLA classification G10L13/08.
  
[List of Patents for class 704 subclass E13.012]    E13.012Grapheme to phoneme, detection of language:
 This subclass is indented under subclass E13.011. This subclass is substantially the same in scope as ECLA classification G10L13/08G.
  
[List of Patents for class 704 subclass E13.013]    E13.013Prosody rules derived from text:
 This subclass is indented under subclass E13.011. This subclass is substantially the same in scope as ECLA classification G10L13/08P.
  
[List of Patents for class 704 subclass E13.014]    E13.014Stress or intonation:
 This subclass is indented under subclass E13.011. This subclass is substantially the same in scope as ECLA classification G10L13/08S.
  
[List of Patents for class 704 subclass E15.001]    E15.001SPEECH RECOGNITION:
 This main group provides for processes, systems, and apparatus for the recognition of speech, including training of speech recognition systems, language recognition, speech classification and search, speech-to-text systems, and evaluation or assessment of speech recognition systems. This subclass is substantially the same in scope as ECLA classification G10L15/00.
  
[List of Patents for class 704 subclass E15.002]    E15.002Assessment or evaluation of speech recognition systems:
 This subclass is indented under subclass E15.001. This subclass is substantially the same in scope as ECLA classification G10L15/00A.
  
[List of Patents for class 704 subclass E15.003]    E15.003Language recognition:
 This subclass is indented under subclass E15.001. This subclass is substantially the same in scope as ECLA classification G10L15/00L.
  
[List of Patents for class 704 subclass E15.004]    E15.004Feature extraction for speech recognition; selection of recognition unit:
 This subclass is indented under subclass E15.001. This subclass is substantially the same in scope as ECLA classification G10L15/02.
  
[List of Patents for class 704 subclass E15.005]    E15.005Segmentation or word limit detection:
 This subclass is indented under subclass E15.001. This subclass is substantially the same in scope as ECLA classification G10L15/04.
  
[List of Patents for class 704 subclass E15.006]    E15.006Word boundary detection:
 This subclass is indented under subclass E15.005. This subclass is substantially the same in scope as ECLA classification G10L15/04W.
  
[List of Patents for class 704 subclass E15.007]    E15.007Creation of reference templates; training of speech recognition systems, e.g., adaptation to the characteristics of the speaker’s voice, etc.:
 This subclass is indented under subclass E15.001. This subclass is substantially the same in scope as ECLA classification G10L15/06.
  
[List of Patents for class 704 subclass E15.008]    E15.008Training:
 This subclass is indented under subclass E15.007. This subclass is substantially the same in scope as ECLA classification G10L15/06T.
  
[List of Patents for class 704 subclass E15.009]    E15.009Adaptation:
 This subclass is indented under subclass E15.007. This subclass is substantially the same in scope as ECLA classification G10L15/06A.
  
[List of Patents for class 704 subclass E15.01]    E15.01In the frequency domain:
 This subclass is indented under subclass E15.009. This subclass is substantially the same in scope as ECLA classification G10L15/06A1.
  
[List of Patents for class 704 subclass E15.011]    E15.011To speaker:
 This subclass is indented under subclass E15.009. This subclass is substantially the same in scope as ECLA classification G10L15/06A3.
  
[List of Patents for class 704 subclass E15.012]    E15.012Supervised, i.e., under machine guidance:
 This subclass is indented under subclass E15.011. This subclass is substantially the same in scope as ECLA classification G10L15/06A3S.
  
[List of Patents for class 704 subclass E15.013]    E15.013Unsupervised:
 This subclass is indented under subclass E15.011. This subclass is substantially the same in scope as ECLA classification G10L15/06A3U.
  
[List of Patents for class 704 subclass E15.014]    E15.014Speech classification or search:
 This subclass is indented under subclass E15.001. This subclass is substantially the same in scope as ECLA classification G10L15/08.
  
[List of Patents for class 704 subclass E15.015]    E15.015Using distance or distortion measures between unknown speech and reference templates:
 This subclass is indented under subclass E15.014. This subclass is substantially the same in scope as ECLA classification G10L15/10.
  
[List of Patents for class 704 subclass E15.016]    E15.016Using dynamic programming techniques, e.g., Dynamic Time Warping (DTW), etc.:
 This subclass is indented under subclass E15.014. This subclass is substantially the same in scope as ECLA classification G10L15/12.
  
[List of Patents for class 704 subclass E15.017]    E15.017Using artificial neural networks:
 This subclass is indented under subclass E15.014. This subclass is substantially the same in scope as ECLA classification G10L15/16.
  
[List of Patents for class 704 subclass E15.018]    E15.018Using natural language modeling:
 This subclass is indented under subclass E15.014. This subclass is substantially the same in scope as ECLA classification G10L15/18.
  
[List of Patents for class 704 subclass E15.019]    E15.019Using context dependencies, e.g., language models, etc. :
 This subclass is indented under subclass E15.018. This subclass is substantially the same in scope as ECLA classification G10L15/18C.
  
[List of Patents for class 704 subclass E15.02]    E15.02Phonemic context, e.g., pronunciation rules, phonotactical constraints, phoneme n-grams, etc. :
 This subclass is indented under subclass E15.019. This subclass is substantially the same in scope as ECLA classification G10L15/18C1.
  
[List of Patents for class 704 subclass E15.021]    E15.021Grammatical context, e.g., disambiguation of the recognition hypotheses based on word sequence rules, etc. :
 This subclass is indented under subclass E15.019. This subclass is substantially the same in scope as ECLA classification G10L15/18C2.
  
[List of Patents for class 704 subclass E15.022]    E15.022Formal grammars, e.g., finite state automata, context free grammars, word networks, etc. :
 This subclass is indented under subclass E15.021. This subclass is substantially the same in scope as ECLA classification G10L15/18C2F.
  
[List of Patents for class 704 subclass E15.023]    E15.023Probabilistic grammars, e.g., word n-grams, etc.:
 This subclass is indented under subclass E15.021. This subclass is substantially the same in scope as ECLA classification G10L15/18C2S.
  
[List of Patents for class 704 subclass E15.024]    E15.024Semantic context, e.g., disambiguation of the recognition hypotheses based on word meaning, etc. :
 This subclass is indented under subclass E15.019. This subclass is substantially the same in scope as ECLA classification G10L15/18C3.
  
[List of Patents for class 704 subclass E15.025]    E15.025Using prosody or stress:
 This subclass is indented under subclass E15.018. This subclass is substantially the same in scope as ECLA classification G10L15/18P.
  
[List of Patents for class 704 subclass E15.026]    E15.026Parsing for meaning understanding:
 This subclass is indented under subclass E15.018. This subclass is substantially the same in scope as ECLA classification G10L15/18U.
  
[List of Patents for class 704 subclass E15.027]    E15.027Using statistical models, e.g., Hidden Marker Models (HMMs), etc.:
 This subclass is indented under subclass E15.014. This subclass is substantially the same in scope as ECLA classification G10L15/14.
  
[List of Patents for class 704 subclass E15.028]    E15.028Hidden Markov Models (HMMs):
 This subclass is indented under subclass E15.027. This subclass is substantially the same in scope as ECLA classification G10L15/14M.
  
[List of Patents for class 704 subclass E15.029]    E15.029Training of Hidden Markov Models (HMMs) :
 This subclass is indented under subclass E15.028. This subclass is substantially the same in scope as ECLA classification G10L15/14M1.
  
[List of Patents for class 704 subclass E15.03]    E15.03With insufficient amount of training data, e.g., state sharing, tying, deleted interpolation, etc. :
 This subclass is indented under subclass E15.029. This subclass is substantially the same in scope as ECLA classification G10L15/14M1S.
  
[List of Patents for class 704 subclass E15.031]    E15.031Duration modeling in Hidden Markov Models (HMMs), e.g., semi- HMM, segmental models, transition probabilities, etc.:
 This subclass is indented under subclass E15.028. This subclass is substantially the same in scope as ECLA classification G10L15/14M2.
  
[List of Patents for class 704 subclass E15.032]    E15.032Hidden Markov Models (HMMs) network:
 This subclass is indented under subclass E15.028. This subclass is substantially the same in scope as ECLA classification G10L15/14M3.
  
[List of Patents for class 704 subclass E15.033]    E15.033State emission probabilities:
 This subclass is indented under subclass E15.028. This subclass is substantially the same in scope as ECLA classification G10L15/14M4.
  
[List of Patents for class 704 subclass E15.034]    E15.034Continuous densities, e.g., Gaussian distribution, Laplace, etc. :
 This subclass is indented under subclass E15.033. This subclass is substantially the same in scope as ECLA classification G10L15/14M4C.
  
[List of Patents for class 704 subclass E15.035]    E15.035Discrete densities, e.g., Vector Quantization preprocessor, look-up tables, etc. :
 This subclass is indented under subclass E15.033. This subclass is substantially the same in scope as ECLA classification G10L15/14M4D.
  
[List of Patents for class 704 subclass E15.036]    E15.036Neural Network (NN) as output probability estimator, e.g., hybrid HMM/NN, etc.:
 This subclass is indented under subclass E15.033. This subclass is substantially the same in scope as ECLA classification G10L15/14M4N.
  
[List of Patents for class 704 subclass E15.037]    E15.037Non-hidden Markov Model:
 This subclass is indented under subclass E15.027. This subclass is substantially the same in scope as ECLA classification G10L15/14N.
  
[List of Patents for class 704 subclass E15.038]    E15.038Recognition networks:
 This subclass is indented under subclass E15.014. This subclass is substantially the same in scope as ECLA classification G10L15/08N.
  
[List of Patents for class 704 subclass E15.039]    E15.039Speech recognition techniques for robustness in adverse environments, e.g., in noise, of stress induced speech, etc.:
 This subclass is indented under subclass E15.001. This subclass is substantially the same in scope as ECLA classification G10L15/20.

SEE OR SEARCH THIS CLASS, SUBCLASS:

E21.002,for speech enhancement.
  
[List of Patents for class 704 subclass E15.04]    E15.04Procedures used during a speech recognition process, e.g., man-machine dialogue, etc.:
 This subclass is in dented under subclass E15.001. This subclass is substantially the same in scope as ECLA classification G10L15/22.
  
[List of Patents for class 704 subclass E15.041]    E15.041Speech recognition using nonacoustical features, e.g., position of the lips, etc.:
 This subclass is indented under subclass E15.001. This subclass is substantially the same in scope as ECLA classification G10L15/24.
  
[List of Patents for class 704 subclass E15.042]    E15.042Using position of the lips, movement of the lips, or face analysis:
 This subclass is indented under subclass E15.041. This subclass is substantially the same in scope as ECLA classification G10L15/24L.
  
[List of Patents for class 704 subclass E15.043]    E15.043Speech to text systems:
 This subclass is indented under subclass E15.001. This subclass is substantially the same in scope as ECLA classification G10L15/26.
  
[List of Patents for class 704 subclass E15.044]    E15.044Speech recognition depending on application context, e.g., in a computer, etc.:
 This subclass is in dented under subclass E15.043. This subclass is substantially the same in scope as ECLA classification G10L15/26C.
  
[List of Patents for class 704 subclass E15.045]    E15.045Systems using speech recognizers:
 This subclass is indented under subclass E15.043. This subclass is substantially the same in scope as ECLA classification G10L15/26A.
  
[List of Patents for class 704 subclass E15.046]    E15.046Constructional details of speech recognition systems:
 This subclass is indented under subclass E15.001. This subclass is substantially the same in scope as ECLA classification G10L15/28.
  
[List of Patents for class 704 subclass E15.047]    E15.047Distributed recognition, e.g., in client-server systems for mobile phones or network applications, etc. :
 This subclass is indented under subclass E15.046. This subclass is substantially the same in scope as ECLA classification G10L15/28D.
  
[List of Patents for class 704 subclass E15.048]    E15.048Memory allocation or algorithm optimization to reduce hardware requirements:
 This subclass is indented under subclass E15.046. This subclass is substantially the same in scope as ECLA classification G10L15/28H.
  
[List of Patents for class 704 subclass E15.049]    E15.049Multiple recognizers used in sequence or in parallel; corresponding voting or score combination systems:
 This subclass is indented under subclass E15.046. This subclass is substantially the same in scope as ECLA classification G10L15/28M.
  
[List of Patents for class 704 subclass E15.05]    E15.05Recognizers for parallel processing:
 This subclass is indented under subclass E15.046. This subclass is substantially the same in scope as ECLA classification G10L15/28P.
  
[List of Patents for class 704 subclass E17.001]    E17.001SPEAKER IDENTIFICATION OR VERIFICATION:
 This main group provides for processes and apparatus for recognizing special voice characteristics, systems using speaker recognizers and details of speaker identification or verification processes or apparatus. This subclass is substantially the same in scope as ECLA classification G10L17/00.
  
[List of Patents for class 704 subclass E17.002]    E17.002Recognition of special voice characteristics, e.g., for use in a lie detector; recognition of animal voices, etc.:
 This subclass is indented under subclass E17.001. This subclass is substantially the same in scope as ECLA classification G10L17/00C.
  
[List of Patents for class 704 subclass E17.003]    E17.003Systems using speaker recognizers:
 This subclass is indented under subclass E17.001. This subclass is substantially the same in scope as ECLA classification G10L17/00U.
  
[List of Patents for class 704 subclass E17.004]    E17.004Details:
 This subclass is indented under subclass E17.001. This subclass is substantially the same in scope as ECLA classification G10L17/00B2.
  
[List of Patents for class 704 subclass E17.005]    E17.005Preprocessing operations, e.g., segment selection, etc.; pattern representation or modeling, e.g. based on linear discriminant analysis (LDA), principal components, etc.; feature selection or extraction:
 This subclass is indented under subclass E17.004. This subclass is substantially the same in scope as ECLA classification G10L17/00B2.
  
[List of Patents for class 704 subclass E17.006]    E17.006Training, model building, enrollment:
 This subclass is in dented under subclass E17.004. This subclass is substantially the same in scope as ECLA classification G10L17/00B6.
  
[List of Patents for class 704 subclass E17.007]    E17.007Decision making techniques, pattern matching strategies:
 This subclass is in dented under subclass E17.004. This subclass is substantially the same in scope as ECLA classification G10L17/00B8.
  
[List of Patents for class 704 subclass E17.008]    E17.008Use of particular distance or distortion metric between probe pattern and reference templates:
 This subclass is indented under subclass E17.007. This subclass is substantially the same in scope as ECLA classification G10L17/00B8D.
  
[List of Patents for class 704 subclass E17.009]    E17.009Multimodal systems, i.e., based on the integration of multiple recognition engines or experts fusion:
 This subclass is indented under subclass E17.007. This subclass is substantially the same in scope as ECLA classification G10L17/00B8M.
  
[List of Patents for class 704 subclass E17.01]    E17.01Score normalization:
 This subclass is indented under subclass E17.007. This subclass is substantially the same in scope as ECLA classification G10L17/00B8N.
  
[List of Patents for class 704 subclass E17.011]    E17.011Use of phonemic categorization or speech recognition prior to speaker recognition or verification:
 This subclass is indented under subclass E17.007. This subclass is substantially the same in scope as ECLA classification G10L17/00B8P.
  
[List of Patents for class 704 subclass E17.012]    E17.012Hidden Markov Models (HMMs):
 This subclass is in dented under subclass E17.004. This subclass is substantially the same in scope as ECLA classification G10L17/00B14.
  
[List of Patents for class 704 subclass E17.013]    E17.013Artificial neural networks, connectionist approaches:
 This subclass is in dented under subclass E17.004. This subclass is substantially the same in scope as ECLA classification G10L17/00B16.
  
[List of Patents for class 704 subclass E17.014]    E17.014Pattern transformations and operations aimed at increasing system robustness, e.g., against channel noise, different working conditions, etc. :
 This subclass is in dented under subclass E17.004. This subclass is substantially the same in scope as ECLA classification G10L17/00B20.
  
[List of Patents for class 704 subclass E17.015]    E17.015Interactive procedures, man-machine interface:
 This subclass is in dented under subclass E17.004. This subclass is substantially the same in scope as ECLA classification G10L17/00B22.
  
[List of Patents for class 704 subclass E17.016]    E17.016User prompted to utter a password or predefined text:
 This subclass is indented under subclass E17.015. This subclass is substantially the same in scope as ECLA classification G10L17/00B22P.
  
[List of Patents for class 704 subclass E19.001]    E19.001SPEECH OR AUDIO SIGNAL ANALYSIS-SYNTHESIS TECHNIQUES FOR REDUNDANCY REDUCTION, E.G., IN VOCODERS, ETC.; CODING OR DECODING OF SPEECH OR AUDIO SIGNALS; COMPRESSION OR EXPANSION OF SPEECH OR AUDIO SIGNALS, E.G., SOURCE-FILTER MODELS, PSYCHOACOUSTIC ANALYSIS, ETC. :
 This main group provides for processes and apparatus for the coding, decoding, compression or expansion of speech or audio signals, including techniques for redundancy reduction, and psychoacoustic analysis. This subclass is substantially the same in scope as ECLA classification G10L19/00.

SEE OR SEARCH THIS CLASS, SUBCLASS:

E21.016,for time compression or expansion of speech waves.
  
[List of Patents for class 704 subclass E19.002]    E19.002Perceptual measures for quality assessment:
 This subclass is in dented under subclass E19.001. This subclass is substantially the same in scope as ECLA classification G10L19/00A.
  
[List of Patents for class 704 subclass E19.003]    E19.003Correction of errors induced by the transmission channel, if related to the coding:
 This subclass is in dented under subclass E19.001. This subclass is substantially the same in scope as ECLA classification G10L19/00E.
  
[List of Patents for class 704 subclass E19.004]    E19.004Lossless audio signal coding; perfect reconstruction of coded audio signal by transmission of coding error:
 This subclass is in dented under subclass E19.001. This subclass is substantially the same in scope as ECLA classification G10L19/00L.
  
[List of Patents for class 704 subclass E19.005]    E19.005Multichannel audio signal coding and decoding, i.e., using interchannel correlation to reduce redundancies, e.g., joint-stereo, intensity-coding, matrixing, etc.:
 This subclass is in dented under subclass E19.001. This subclass is substantially the same in scope as ECLA classification G10L19/00M.
  
[List of Patents for class 704 subclass E19.006]    E19.006Comfort noise, silence coding:
 This subclass is in dented under subclass E19.001. This subclass is substantially the same in scope as ECLA classification G10L19/00N.
  
[List of Patents for class 704 subclass E19.007]    E19.007Speech coding using phonetic or linguistical decoding of the source; reconstruction using text-to-speech synthesis:
 This subclass is in dented under subclass E19.001. This subclass is substantially the same in scope as ECLA classification G10L19/00S.
  
[List of Patents for class 704 subclass E19.008]    E19.008Systems using vocoders:
 This subclass is in dented under subclass E19.001. This subclass is substantially the same in scope as ECLA classification G10L19/00U.
  
[List of Patents for class 704 subclass E19.009]    E19.009Audio watermarking, i.e., embedding inaudible data in the audio signal:
 This subclass is in dented under subclass E19.001. This subclass is substantially the same in scope as ECLA classification G10L19/00W.
  
[List of Patents for class 704 subclass E19.01]    E19.01Using spectral analysis, e.g., transform vocoders, subband vocoders, perceptual audio coders, psychoacoustically based lossy encoding, etc., e.g., MPEG audio, Dolby AC-3, etc.:
 This subclass is indented under subclass E19.001. This subclass is substantially the same in scope as ECLA classification G10L19/02.
  
[List of Patents for class 704 subclass E19.011]    E19.011Blocking, i.e., grouping of samples in time, choice of analysis window, overlap factor:
 This subclass is in dented under subclass E19.01. This subclass is substantially the same in scope as ECLA classification G10L19/02B.
  
[List of Patents for class 704 subclass E19.012]    E19.012Detection of transients and attacks for time/ frequency resolution switching:
 This subclass is in dented under subclass E19.011. This subclass is substantially the same in scope as ECLA classification G10L19/02B1.
  
[List of Patents for class 704 subclass E19.013]    E19.013Noise substitution, i.e., substituting nontonal spectral components by noisy source:
 This subclass is in dented under subclass E19.01. This subclass is substantially the same in scope as ECLA classification G10L19/02N.

SEE OR SEARCH THIS CLASS, SUBCLASS:

E19.006,for comfort noise for discontinuous speech transmission.
  
[List of Patents for class 704 subclass E19.014]    E19.014Spectral prediction for pre-echo prevention; temporal noise shaping (TNS), e.g., in MPEG2 or MPEG4, etc.:
 This subclass is in dented under subclass E19.01. This subclass is substantially the same in scope as ECLA classification G10L19/02P.
  
[List of Patents for class 704 subclass E19.015]    E19.015Quantization or dequantization of spectral components:
 This subclass is in dented under subclass E19.01. This subclass is substantially the same in scope as ECLA classification G10L19/02Q.
  
[List of Patents for class 704 subclass E19.016]    E19.016Scalar quantization:
 This subclass is in dented under subclass E19.015. This subclass is substantially the same in scope as ECLA classification G10L19/02Q2.
  
[List of Patents for class 704 subclass E19.017]    E19.017Vector quantization, e.g., Twin-VQ audio, etc.:
 This subclass is in dented under subclass E19.015. This subclass is substantially the same in scope as ECLA classification G10L19/02Q4.
  
[List of Patents for class 704 subclass E19.018]    E19.018Using subband decomposition:
 This subclass is indented under subclass E19.01. This subclass is substantially the same in scope as ECLA classification G10L19/02S.
  
[List of Patents for class 704 subclass E19.019]    E19.019Subband vocoders:
 This subclass is in dented under subclass E19.018. This subclass is substantially the same in scope as ECLA classification G10L19/02S1.
  
[List of Patents for class 704 subclass E19.02]    E19.02Using orthogonal transformation:
 This subclass is in dented under subclass E19.01. This subclass is substantially the same in scope as ECLA classification G10L19/02T.
  
[List of Patents for class 704 subclass E19.021]    E19.021Using wavelet decomposition:
 This subclass is in dented under subclass E19.02. This subclass is substantially the same in scope as ECLA classification G10L19/02T2.
  
[List of Patents for class 704 subclass E19.022]    E19.022Dynamic bit allocation:
 This subclass is in dented under subclass E19.001. This subclass is substantially the same in scope as ECLA classification G10L19/00B.
  
[List of Patents for class 704 subclass E19.023]    E19.023Using predictive techniques; codecs based on source-filter modelization:
 This subclass is in dented under subclass E19.001. This subclass is substantially the same in scope as ECLA classification G10L19/04.
  
[List of Patents for class 704 subclass E19.024]    E19.024Determination or coding of the spectral characteristics, e.g., of the short-term prediction coefficients, etc. :
 This subclass is in dented under subclass E19.023. This subclass is substantially the same in scope as ECLA classification G10L19/06.
  
[List of Patents for class 704 subclass E19.025]    E19.025Line spectrum pair (LSP) vocoders:
 This subclass is in dented under subclass E19.024. This subclass is substantially the same in scope as ECLA classification G10L19/06L.
  
[List of Patents for class 704 subclass E19.026]    E19.026Determination or coding of the excitation function; determination or coding of the long-term prediction characteristics:
 This subclass is in dented under subclass E19.023. This subclass is substantially the same in scope as ECLA classification G10L19/08.
  
[List of Patents for class 704 subclass E19.027]    E19.027Determination or coding of an excitation gain:
 This subclass is in dented under subclass E19.026. This subclass is substantially the same in scope as ECLA classification G10L19/08G.
  
[List of Patents for class 704 subclass E19.028]    E19.028Using mixed excitation model, e.g., MELP, MBE, Split band LPC, HVXC , etc.:
 This subclass is in dented under subclass E19.026. This subclass is substantially the same in scope as ECLA classification G10L19/08M.
  
[List of Patents for class 704 subclass E19.029]    E19.029Long-term prediction, i.e., removing periodical redundancies, e.g., adaptive codebook, pitch predictor, etc.:
 This subclass is in dented under subclass E19.026. This subclass is substantially the same in scope as ECLA classification G10L19/08P.
  
[List of Patents for class 704 subclass E19.03]    E19.03Using sinusoidal excitation model:
 This subclass is in dented under subclass E19.026. This subclass is substantially the same in scope as ECLA classification G10L19/08S.
  
[List of Patents for class 704 subclass E19.031]    E19.031Using prototype waveform decomposition or waveform interpolative coders (PWI):
 This subclass is in dented under subclass E19.026. This subclass is substantially the same in scope as ECLA classification G10L19/08W.
  
[List of Patents for class 704 subclass E19.032]    E19.032Determination or coding of a multipulse excitation:
 This subclass is in dented under subclass E19.026. This subclass is substantially the same in scope as ECLA classification G10L19/10.
  
[List of Patents for class 704 subclass E19.033]    E19.033Algebraic codebook; sparse pulse excitation:
 This subclass is in dented under subclass E19.032. This subclass is substantially the same in scope as ECLA classification G10L19/10A.
  
[List of Patents for class 704 subclass E19.034]    E19.034Regular pulse excitation:
 This subclass is indented under subclass E19. 032. This subclass is substantially the same in scope as ECLA classification G10L19/10R.
  
[List of Patents for class 704 subclass E19.035]    E19.035Determination or coding of a code excitation; code excited linear prediction (CELP) vocoders:
 This subclass is in dented under subclass E19.026. This subclass is substantially the same in scope as ECLA classification G10L19/12.
  
[List of Patents for class 704 subclass E19.036]    E19.036Pitch excitation, e.g., PSI-CELP (pitch synchronous innovation CELP), etc.:
 This subclass is in dented under subclass E19.035. This subclass is substantially the same in scope as ECLA classification G10L19/12P.
  
[List of Patents for class 704 subclass E19.037]    E19.037Residual excited linear prediction (RELP):
 This subclass is in dented under subclass E19.035. This subclass is substantially the same in scope as ECLA classification G10L19/12R.
  
[List of Patents for class 704 subclass E19.038]    E19.038Vector sum excited linear prediction (VSELP):
 This subclass is in dented under subclass E19.035. This subclass is substantially the same in scope as ECLA classification G10L19/12V.
  
[List of Patents for class 704 subclass E19.039]    E19.039Details of speech and audio coders:
 This subclass is indented under subclass E19.023. This subclass is substantially the same in scope as ECLA classification G10L19/14.
  
[List of Patents for class 704 subclass E19.04]    E19.04Vocoder architecture:
 This subclass is in dented under subclass E19.039. This subclass is substantially the same in scope as ECLA classification G10L19/14A.
  
[List of Patents for class 704 subclass E19.041]    E19.041Vocoders using multiple modes:
 This subclass is in dented under subclass E19.04. This subclass is substantially the same in scope as ECLA classification G10L19/14A1.
  
[List of Patents for class 704 subclass E19.042]    E19.042Using sound class specific coding, hybrid encoders, object- based coding:
 This subclass is in dented under subclass E19.041. This subclass is substantially the same in scope as ECLA classification G10L19/14A1C.
  
[List of Patents for class 704 subclass E19.043]    E19.043Mode decision, i.e., based on audio signal content versus external parameter:
 This subclass is in dented under subclass E19.041. This subclass is substantially the same in scope as ECLA classification G10L19/14A1D.
  
[List of Patents for class 704 subclass E19.044]    E19.044Variable rate or variable quality codecs, e.g., scalable representation encoding, etc.:
 This subclass is in dented under subclass E19.041. This subclass is substantially the same in scope as ECLA classification G10L19/14A1R.
  
[List of Patents for class 704 subclass E19.045]    E19.045Pre- or post-filtering:
 This subclass is in dented under subclass E19.039. This subclass is substantially the same in scope as ECLA classification G10L19/14P.
  
[List of Patents for class 704 subclass E19.046]    E19.046Pre-filtering, e.g., high frequency emphasis prior to encoding, etc.:
 This subclass is in dented under subclass E19.045. This subclass is substantially the same in scope as ECLA classification G10L19/14P1.
  
[List of Patents for class 704 subclass E19.047]    E19.047Post-filtering, e.g., pitch enhancement, formant emphasis for decoder, etc.:
 This subclass is in dented under subclass E19.045. This subclass is substantially the same in scope as ECLA classification G10L19/14P2.
  
[List of Patents for class 704 subclass E19.048]    E19.048Audio streaming, i.e., formatting and decoding of an encoded audio signal:
 This subclass is in dented under subclass E19.039. This subclass is substantially the same in scope as ECLA classification G10L19/14S.
  
[List of Patents for class 704 subclass E19.049]    E19.049Transcoding, i.e., converting between two coded representations avoiding cascaded coding-decoding:
 This subclass is in dented under subclass E19.039. This subclass is substantially the same in scope as ECLA classification G10L19/14T.
  
[List of Patents for class 704 subclass E21.001]    E21.001MODIFICATION OF AT LEAST ONE CHARACTERISTIC OF SPEECH WAVES:
 This main group provides for processes and apparatus for modifying at least one characteristic of a speech signal. This subclass is substantially the same in scope as ECLA classification G10L21/00.
  
[List of Patents for class 704 subclass E21.002]    E21.002Speech enhancement, e.g., noise reduction, echo cancellation, etc.:
 This subclass is in dented under subclass E21.001. This subclass is substantially the same in scope as ECLA classification G10L21/02.
  
[List of Patents for class 704 subclass E21.003]    E21.003Applications:
 This subclass is in dented under subclass E21.002. This subclass is substantially the same in scope as ECLA classification G10L21/02A.
  
[List of Patents for class 704 subclass E21.004]    E21.004Speech corrupted by noise:
 This subclass is in dented under subclass E21.003. This subclass is substantially the same in scope as ECLA classification G10L21/02A1.
  
[List of Patents for class 704 subclass E21.005]    E21.005Periodic noise:
 This subclass is in dented under subclass E21.004. This subclass is substantially the same in scope as ECLA classification G10L21/02A1N.
  
[List of Patents for class 704 subclass E21.006]    E21.006The noise being separate speech:
 This subclass is indented under subclass E21.004. This subclass is substantially the same in scope as ECLA classification G10L21/02A1S.
  
[List of Patents for class 704 subclass E21.007]    E21.007Speech corrupted by echo-reverberation:
 This subclass is in dented under subclass E21.003. This subclass is substantially the same in scope as ECLA classification G10L21/02A2.
  
[List of Patents for class 704 subclass E21.008]    E21.008Speech corrupted by stress-Lombard effect:
 This subclass is in dented under subclass E21.003. This subclass is substantially the same in scope as ECLA classification G10L21/02A3.
  
[List of Patents for class 704 subclass E21.009]    E21.009Enhancement of intelligibility of clean or coded speech:
 This subclass is in dented under subclass E21.003. This subclass is substantially the same in scope as ECLA classification G10L21/02A4.
  
[List of Patents for class 704 subclass E21.01]    E21.01Enhancement of diverse speech:
 This subclass is indented under subclass E21.009. This subclass is substantially the same in scope as ECLA classification G10L21/02A4D.
  
[List of Patents for class 704 subclass E21.011]    E21.011Bandwidth extension taking place at the receiving side, e.g., generation of low- or high-frequency components, regeneration of spectral holes, etc.:
 This subclass is indented under subclass E21.009. This subclass is substantially the same in scope as ECLA classification G10L21/02A4E.
  
[List of Patents for class 704 subclass E21.012]    E21.012Separate reconstruction of interference and of speech signal:
 This subclass is indented under subclass E21.003. This subclass is substantially the same in scope as ECLA classification G10L21/02A6.
  
[List of Patents for class 704 subclass E21.013]    E21.013The interference being a separate speaker:
 This subclass is in dented under subclass E21.012. This subclass is substantially the same in scope as ECLA classification G10L21/02A6S.
  
[List of Patents for class 704 subclass E21.014]    E21.014Active noise canceling:
 This subclass is in dented under subclass E21.003. This subclass is substantially the same in scope as ECLA classification G10L21/02A7.
  
[List of Patents for class 704 subclass E21.015]    E21.015Public address system:
 This subclass is in dented under subclass E21.003. This subclass is substantially the same in scope as ECLA classification G10L21/02A8.
  
[List of Patents for class 704 subclass E21.016]    E21.016Suppression or repetition of time signal segments:
 This subclass is indented under subclass E21.002. This subclass is substantially the same in scope as ECLA classification G10L21/02R.
  
[List of Patents for class 704 subclass E21.017]    E21.017Time compression or expansion:
 This subclass is in dented under subclass E21.001. This subclass is substantially the same in scope as ECLA classification G10L21/04.
  
[List of Patents for class 704 subclass E21.018]    E21.018Suppression or repetition of time signal segments:
 This subclass is in dented under subclass E21.017. This subclass is substantially the same in scope as ECLA classification G10L21/04R.
  
[List of Patents for class 704 subclass E21.019]    E21.019Transformation of speech into a nonaudible representation, e.g., speech visualization, speech processing for tactile aids, etc. :
 This subclass is in dented under subclass E21.001. This subclass is substantially the same in scope as ECLA classification G10L21/06.
  
[List of Patents for class 704 subclass E21.02]    E21.02Synchronization of speech with image or synthesis of the lips movement from speech, e.g., for "talking heads," etc.:
 This subclass is in dented under subclass E21.019. This subclass is substantially the same in scope as ECLA classification G10L21/06L.
  

This page is produced by the Office of Classification Support (Office of Patent Classification) for the Reference Tools Project.

Please send questions and comments to usptoinfo@uspto.gov .

Note: The Patent and Trademark Depository Library Program (PTDLP) administers a nationwide network of public, state and academic libraries designated as Patent and Trademark Depository Libraries authorized by 35 U.S.C. 13 to: Disseminate Patent and Trademark Information Support Diverse Intellectual Property Needs of the Public. PTDL Contact Information

Note: For information/comments on electronic information products, such as purchasing USPTO data, or to discuss system requirements for magnetic tape products, contact:

     Information Products Division -- U.S. Patent and Trademark Office Information Products Division Contact Information
     Or, browse their on-line catalog.

KEY: e Biz=online business system fees=fees forms=formshelp=help laws and regs=laws/regulations definition=definition (glossary)

The Inventors Assistance Center is available to help you on patent matters.Send questions about USPTO programs and services to the USPTO Contact Center (UCC). You can suggest USPTO webpages or material you would like featured on this section by E-mail to the webmaster@uspto.gov. While we cannot promise to accommodate all requests, your suggestions will be considered and may lead to other improvements on the website.


|.HOME | SITE INDEX| SEARCH | eBUSINESS | HELP | PRIVACY POLICY