| US 7,516,070 B2 | ||
| Method for simultaneously creating audio-aligned final and verbatim text with the assistance of a speech recognition program as may be useful in form completion using a verbal entry method | ||
| Jonathan Kahn, Crown Point, Ind. (US) | ||
| Assigned to Custom Speech USA, INc., Crown Point, Ind. (US) | ||
| Appl. No. 10/545,584 PCT Filed Feb. 19, 2004, PCT No. PCT/US2004/004984 § 371(c)(1), (2), (4) Date Apr. 05, 2006, PCT Pub. No. WO2004/075027, PCT Pub. Date Sep. 02, 2004. |
||
| Prior Publication US 2006/0167686 A1, Jul. 27, 2006 | ||
| Int. Cl. G10L 15/00 (2006.01) | ||
| U.S. Cl. 704—235 [704/277] | 24 Claims |
| 1. A method for creating audio-aligned final and verbatim text from a transcribed session file for form completion, comprising:
(a) transcribing audio into a transcribed text using a speech recognition software;
(b) aligning segments of the audio with segments of the transcribed text;
(c) displaying the transcribed text in a graphical user interface;
(d) creating a verbatim text and a final text from the transcribed text such that segments of the verbatim text and the final
text maintain alignment with the audio segments;
(e) simultaneously correcting the verbatim text and the final text by selectively listening to the audio aligned thereto;
(f) simultaneously correcting the verbatim text and the final text by selectively copying and pasting text from a previously
created text;
(g) unlocking the verbatim text from the final text and selectively correcting one of the verbatim text and the final text
by selectively listening to the audio aligned thereto; and
(h) unlocking the verbatim text from the final text and selectively copying and pasting text from the previously created text
into one of the verbatim text and the final text.
|