US 11,818,300 B2
Processing system, processing method, and non-transitory storage medium
Hiroki Matsuura, Tokyo (JP); Shuji Komeiji, Tokyo (JP); Takayuki Shirokaze, Tokyo (JP); and Ryoji Yoshida, Tokyo (JP)
Assigned to NEC CORPORATION, Tokyo (JP)
Filed by NEC Corporation, Tokyo (JP)
Filed on Oct. 3, 2022, as Appl. No. 17/958,543.
Application 17/958,543 is a continuation of application No. 17/312,170, granted, now 11,503,161, previously published as PCT/JP2019/036062, filed on Sep. 13, 2019.
Claims priority of application No. 2018-231461 (JP), filed on Dec. 11, 2018.
Prior Publication US 2023/0027992 A1, Jan. 26, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04M 3/56 (2006.01); G10L 15/06 (2013.01); H04M 3/428 (2006.01); H04M 3/493 (2006.01)
CPC H04M 3/56 (2013.01) [G10L 15/063 (2013.01); H04M 3/4285 (2013.01); H04M 3/493 (2013.01)] 7 Claims
OG exemplary drawing
 
1. A processing system comprising:
at least one memory configured to store one or more instructions; and
at least one processor configured to execute the one or more instructions to:
make a call between a calling party and an operator;
acquire target speech data in which target speech of the calling party is recorded or a target feature value that indicates a feature of the target speech is included;
infer a language of the target speech, based on an inference model that provides an output language of speech from input speech data in which the speech is recorded or a speech feature value that indicates a feature of the speech, and the target speech data or the target feature value;
output an inference result indicating the language of the target speech;
refer to interpretation staff information in which an interpreter for each of a plurality of languages and contact information are registered and extract the interpreter for the language indicated by the inference result;
output information indicating the extracted interpreter;
place the call between the calling party and the operator on hold, start a call between the operator and the extracted interpreter, and reproduce the target speech data in the call between the operator and the extracted interpreter; and
start a three-party call including the calling party, the operator, and the extracted interpreter when receiving a predetermined input after reproducing the target speech data in the call between the operator and the extracted interpreter.