UPDATING A VOICE TEMPLATE

• US 20140278414A1
• Filed: 05/27/2014
• Published: 09/18/2014
• Est. Priority Date: 10/27/2008
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Miki, Yukari, Noguchi, Masami
• Granted Patent: US 10,621,974 B2
• Time in Patent Office: Days
• US Class Current: 704/244
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 17/04 Training, enrolment or model building
• CPC Class Codes: G10L 2015/0635 updating or merging of old and new templates; Mean values; Weighting

Abstract

Updating a voice template for recognizing a speaker on the basis of a voice uttered by the speaker is disclosed. Stored voice templates indicate distinctive characteristics of utterances from speakers. Distinctive characteristics are extracted for a specific speaker based on a voice message utterance received from that speaker. The distinctive characteristics are compared to the characteristics indicated by the stored voice templates to selected a template that matches within a predetermined threshold. The selected template is updated on the basis of the extracted characteristics.

Claims

1-20. -20. (canceled)

21. A computer-implemented method, comprising:

extracting, from a voice message uttered by a specific speaker, distinctive characteristics of the specific speaker;

selecting, from a plurality of stored voice templates, a voice template based upon a degree of similarity between the extracted distinctive characteristics and distinctive characteristics indicated by the selected voice template; and

updating the selected specific voice template based upon the extracted distinctive characteristics.

22. The method of claim 21, wherein

the voice template is selected from a plurality of candidate templates that are selected based upon a history of exchange of voice messages of an addressee of the voice message.

23. The method of claim 22, wherein

each of the plurality of candidate templates indicates distinctive characteristics uttered by a corresponding one of a plurality of speakers with which the addressee has exchanged voice messages.

24. The method of claim 21, wherein

the selecting is based upon the degree of similarity between the extracted distinctive characteristics and the distinctive characteristics indicated by the selected voice template exceeding a predetermined threshold value.

25. The method of claim 21, wherein

the voice message is exchanged between the specific speaker and a speaker other than the specific speaker via a telephone line, and

the voice message from which the distinctive characteristics are extracted is obtained from a specific telephone line.

26. The method of claim 21, wherein

the voice template is selected from a plurality of candidate templates that are selected based upon a keyword extracted from the voice message.

27. A computer hardware system, comprising:

at least one processor, wherein the at least one processor is configured to initiate and/or perform;

extracting, from a voice message uttered by a specific speaker, distinctive characteristics of the specific speaker;

selecting, from a plurality of stored voice templates, a voice template based upon a degree of similarity between the extracted distinctive characteristics and distinctive characteristics indicated by the selected voice template; and

updating the selected specific voice template based upon the extracted distinctive characteristics.

28. The system of claim 27, wherein

the voice template is selected from a plurality of candidate templates that are selected based upon a history of exchange of voice messages of an addressee of the voice message.

29. The system of claim 28, wherein

each of the plurality of candidate templates indicates distinctive characteristics uttered by a corresponding one of a plurality of speakers with which the addressee has exchanged voice messages.

30. The system of claim 27, wherein

the selecting is based upon the degree of similarity between the extracted distinctive characteristics and the distinctive characteristics indicated by the selected voice template exceeding a predetermined threshold value.

31. The system of claim 27, wherein

the voice message is exchanged between the specific speaker and a speaker other than the specific speaker via a telephone line, and

the voice message from which the distinctive characteristics are extracted is obtained from a specific telephone line.

32. The system of claim 27, wherein

the voice template is selected from a plurality of candidate templates that are selected based upon a keyword extracted from the voice message.

33. A computer program product, comprising:

a computer readable storage medium having stored therein computer readable program code,

the computer readable program code, which when executed by a computer hardware system, causes the computer hardware system to perform;

extracting, from a voice message uttered by a specific speaker, distinctive characteristics of the specific speaker;

selecting, from a plurality of stored voice templates, a voice template based upon a degree of similarity between the extracted distinctive characteristics and distinctive characteristics indicated by the selected voice template; and

updating the selected specific voice template based upon the extracted distinctive characteristics, and

the computer readable storage medium is not a transitory, propagating signal per se.

34. The computer program product of claim 33, wherein

the voice template is selected from a plurality of candidate templates that are selected based upon a history of exchange of voice messages of an addressee of the voice message.

35. The computer program product of claim 34, wherein

each of the plurality of candidate templates indicates distinctive characteristics uttered by a corresponding one of a plurality of speakers with which the addressee has exchanged voice messages.

36. The computer program product of claim 33, wherein

the selecting is based upon the degree of similarity between the extracted distinctive characteristics and the distinctive characteristics indicated by the selected voice template exceeding a predetermined threshold value.

37. The computer program product of claim 33, wherein

the voice message is exchanged between the specific speaker and a speaker other than the specific speaker via a telephone line, and

the voice message from which the distinctive characteristics are extracted is obtained from a specific telephone line.

38. The computer program product of claim 33, wherein

the voice template is selected from a plurality of candidate templates that are selected based upon a keyword extracted from the voice message.