Method and system for using conversational biometrics and speaker identification/verification to filter voice streams
AssigneeInternational Business Machines Corporation
InventorsPeeyush Jaiswal, Naveen Narayan
Life of this patent
Estimating the term…
Abstract
A method and system for using conversational biometrics and speaker identification and/or verification to filter voice streams during mixed mode communication. The method includes receiving an audio stream of a communication between participants. Additionally, the method includes filtering the audio stream of the communication into separate audio streams, one for each of the participants. Each of the separate audio streams contains portions of the communication attributable to a respective participant. Furthermore, the method includes outputting the separate audio streams to a storage system.
Claims20
A method comprising:
- filtering by a computing device an audio stream of a communication into separate audio streams corresponding, respectively, to each of a plurality of participants in the communication, wherein each of the separate audio streams contains portions of the communication attributable to the corresponding one of the plurality of participants;
- identifying by the computing device the plurality of participants by matching one or more of the portions of the communication in each of the separate audio streams to voice prints;
- and
- subsequently in the communication, comparing by the computing device the separate audio streams to only a plurality of the voice prints corresponding to the identified participants within the communication.
A system comprising:
- one or more sensors sensor;
- and
- a computing device including a conversational biometrics analysis and speaker identification-verification (CB/SIV) tool,
- wherein the CB/SIV controls the computing device to:
- filter an audio stream received via the one or more sensors into separate audio streams corresponding, respectively, to each of a plurality of participants in the communication, wherein each of the separate audio streams contains portions of the communication attributable to the corresponding one of the plurality of participants;
- identify the plurality of participants by matching one or more of the portions of the communication in each of the separate audio streams to voice prints;
- and
- compare the separate audio streams to only to a plurality of the voice prints corresponding to the identified participants within that conversation.
Dependencies are inferred from the claim text.