Voice pattern coding sequence and cataloging voice matching system

• US 9,786,271 B1
• Filed: 09/28/2016
• Issued: 10/10/2017
• Est. Priority Date: 09/28/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Combs, Judith M., Jaiswal, Peeyush, Jaiswal, Priyansh, Jaramillo, David, Tomko, Annita
• Primary Examiner(s): Thomas-Homescu, Anne
• Application Number:
  US15/278,073
• Time in Patent Office: 377 Days
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/0635 updating or merging of old and new templates; Mean values; Weighting
• CPC Class Codes: G10L 25/51 for comparison or discrimination

Abstract

A method for voice pattern coding and catalog matching. The method includes identifying a set of vocal variables for a user, by a voice recognition system, based, at least in part, on a user interaction with the voice recognition system. The method further includes generating a voice model of speech patterns that represent the speaking of a particular language using the identified set of vocal variables, wherein the voice model is adapted to improve recognition of the user'"'"'s voice by the voice recognition system. The method further includes matching the generated voice model to a catalog of speech patterns, and identifying a voice model code that represents speech patterns in the catalog that match the generated voice model. The method further includes providing the identified voice model code to the user.

Claims

1. A computer-implemented method comprising:

identifying a set of vocal variables for a user, by a voice recognition system, based, at least in part, on a user interaction with the voice recognition system, wherein the user interaction includes the user selecting a first language and a second language, and adjusting a level of accent, wherein the level of accent indicates an amount by which the second language affects the user'"'"'s speaking of the first language;

generating, by the voice recognition system, a voice model of speech patterns that represent the user'"'"'s speaking of the first language using the identified set of vocal variables, wherein the voice model is adapted to improve recognition of the user'"'"'s voice by the voice recognition system;

matching, by the voice recognition system, the generated voice model to a catalog of speech patterns, and identifying a voice model code that represents speech patterns in the catalog that match the generated voice model;

providing, by the voice recognition system, the identified voice model code to the user;

receiving, by the voice recognition system, voice input from the user; and

utilizing, by the voice recognition system, the generated voice model to improve recognition of the received voice input, based on the user providing the identified voice model code.

2. The computer-implemented method of claim 1, further comprising:

receiving, by the voice recognition system, voice input and a corresponding voice model code from a second user; and

utilizing, by the voice recognition system, a voice model corresponding to the received voice model code in the catalog to improve recognition of the received voice input.

3. The computer-implemented method of claim 1, wherein matching, by the voice recognition system, the generated voice model to a catalog of speech patterns comprises:

determining, by the voice recognition system, that a speech pattern of the generated voice model does not match any of the speech patterns in the catalog; and

saving, by the voice recognition system, to the catalog, the speech pattern of the generated voice model that does not match any of the speech patterns in the catalog.

4. The computer-implemented method of claim 1, further comprising:

prior to matching the generated voice model to the catalog of voice models, determining, by the voice recognition system, that the generated voice model is accepted by the user.

5. The computer-implemented method of claim 1, further comprising:

upon determining that the generated voice model is not accepted by the user, updating, by the voice recognition system, the generated voice model according to user feedback, wherein the user feedback includes the user further adjusting the level of accent.

6. The computer-implemented method of claim 1, wherein the set of vocal variables includes at least an influence of a geographic background on the user'"'"'s speech pattern.

7. The computer-implemented method of claim 1, wherein the user interaction with the voice recognition system includes the user providing initial voice input to the voice recognition system.

8. The computer-implemented method of claim 6, wherein the set of vocal variables further includes at least an accent of the user'"'"'s speech.

9. The computer-implemented method of claim 8, wherein the set of vocal variables further includes a tone, an inflection, and a lung force.

10. A computer program product comprising:

one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, wherein the one or more computer readable storage media are not transitory signals per se, the program instructions comprising;

program instructions to identify a set of vocal variables for a user, by a voice recognition system, based, at least in part, on a user interaction with the voice recognition system, wherein the user interaction includes the user selecting a first language and a second language, and adjusting a level of accent, wherein the level of accent indicates an amount by which the second language affects the user'"'"'s speaking of the first language;

program instructions to generate a voice model of speech patterns that represent the user'"'"'s speaking of the first language using the identified set of vocal variables, wherein the voice model is adapted to improve recognition of the user'"'"'s voice by the voice recognition system;

program instructions to match the generated voice model to a catalog of speech patterns, and identify a voice model code that represents speech patterns in the catalog that match the generated voice model;

program instructions to provide the identified voice model code to the user;

program instructions to receive voice input from the user; and

program instructions to utilize the generated voice model to improve recognition of the received voice input, based on the user providing the identified voice model code.

11. The computer program product of claim 10, further comprising:

program instructions to receive voice input and a corresponding voice model code from a second user; and

program instructions to utilize a voice model corresponding to the received voice model code in the catalog to improve recognition of the received voice input.

12. The computer program product of claim 10, wherein the program instructions to match the generated voice model to a catalog of speech patterns comprise:

program instructions to determine that a speech pattern of the generated voice model does not match any of the speech patterns in the catalog; and

program instructions to save to the catalog, the speech pattern of the generated voice model that does not match any of the speech patterns in the catalog.

13. The computer program product of claim 10, further comprising:

program instructions to, prior to matching the generated voice model to the catalog of voice models, determine that the generated voice model is accepted by the user.

14. A computer system comprising:

one or more computer processors;

one or more computer readable storage media;

program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising;

18

program instructions to identify a set of vocal variables for a user, by a voice recognition system, based, at least in part, on a user interaction with the voice recognition system, wherein the user interaction includes the user selecting a first language and a second language, and adjusting a level of accent, wherein the level of accent indicates an amount by which the second language affects the user'"'"'s speaking of the first language;

program instructions to generate a voice model of speech patterns that represent the user'"'"'s speaking of the first language using the identified set of vocal variables, wherein the voice model is adapted to improve recognition of the user'"'"'s voice by the voice recognition system;

program instructions to match the generated voice model to a catalog of speech patterns, and identify a voice model code that represents speech patterns in the catalog that match the generated voice model;

program instructions to provide the identified voice model code to the user;

program instructions to receive voice input from the user; and

program instructions to utilize the generated voice model to improve recognition of the received voice input, based on the user providing the identified voice model code.

15. The computer system of claim 14, further comprising:

program instructions to receive voice input and a corresponding voice model code from a second user; and

program instructions to utilize a voice model corresponding to the received voice model code in the catalog to improve recognition of the received voice input.

16. The computer system of claim 14, wherein the program instructions to match the generated voice model to a catalog of speech patterns comprise:

program instructions to determine that a speech pattern of the generated voice model does not match any of the speech patterns in the catalog; and

program instructions to save to the catalog, the speech pattern of the generated voice model that does not match any of the speech patterns in the catalog.

17. The computer system of claim 14, further comprising:

program instructions to, prior to matching the generated voice model to the catalog of voice models, determine that the generated voice model is accepted by the user.