Rapid speech recognition adaptation using acoustic input

• US 9,940,926 B2
• Filed: 06/02/2015
• Issued: 04/10/2018
• Est. Priority Date: 06/02/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Connell, II, Jonathan H., Marcheret, Etienne
• Primary Examiner(s): Goddard, Tammy Paige
• Assistant Examiner(s): Shah, Bharatkumar S
• Application Number:
  US14/728,528
• Publication Number:
  US 20160358609A1
• Time in Patent Office: 1,043 Days
• Field of Search: 704244
• CPC Class Codes: G10L 15/075 supervised, i.e. under machine guidance
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 17/00 Speaker identification or verification techniques
• CPC Class Codes: G10L 17/02 Preprocessing operations, e.g. segment selection; Pattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal components; Feature selection or extraction
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units

Abstract

A method includes the following steps. An acoustic input is obtained from a user, including issuing a verbal prompt to the user and receiving the acoustic input from the user in response to the verbal prompt. One or more acoustic representations are obtained, wherein the one or more acoustic representations are generated from a list of expected responses to the issued verbal prompt. The acoustic input from the user is compared to the one or more acoustic representations. One or more speech recognition parameters are adjusted based on the comparison.

Claims

1. An apparatus, comprising:

a memory; and

a processor operatively coupled to the memory and configured to;

receive one or more speech recognition parameters prior to issuing a verbal prompt to a user;

issue the verbal prompt to the user;

receive an acoustic input from the user in response to the verbal prompt;

process one or more sequences of phonemes to obtain one or more acoustic representations, wherein the one or more sequences of phonemes are generated from a list of expected responses to the issued verbal prompt;

compare the acoustic input from the user to the one or more acoustic representations to determine an acoustic channel characterization and/or speaker class; and

adjust one or more speech recognition parameters based on the comparison, wherein the adjustment comprises an application of feature space mapping to the acoustic input, and further wherein the one or more adjusted speech recognition parameters are used to adapt a speech recognition module of a speech recognition system to use an acoustic model that is consistent with the acoustic channel characterization and/or speaker class so that the selected acoustic model is used for decoding subsequent acoustic input provided by the user as the conversation progresses.

2. The apparatus of claim 1, wherein the comparison comprises a performance of a channel estimation on the acoustic input.

3. The apparatus of claim 1, wherein the comparison comprises a performance of a spectral adaptation on the acoustic input.

4. The apparatus of claim 1, wherein the comparison comprises a performance of a voice print analysis on the acoustic input.

5. The apparatus of claim 1, wherein the comparison comprises a performance of a variable template matching on the acoustic input.

6. The apparatus of claim 1, wherein the adjustment comprises a detection of a class of speaker based on the comparison results.

7. The apparatus of claim 6, wherein the adjustment further comprises a selection of an acoustic model for the detected class of speaker.

18. The apparatus of claim 1, wherein the issued verbal prompt is selected from a database.

19. The apparatus of claim 1, wherein the processing of the one or more sequences of phonemes comprises a generation of one or more sequences of voice frequency estimates in a given format.

8. An article of manufacture comprising a computer readable storage medium for storing computer readable program code which, when executed, causes a computer to:

receive one or more speech recognition parameters prior to issuing a verbal prompt to a user;

issue the verbal prompt to the user;

receive an acoustic input from the user in response to the verbal prompt;

process one or more sequences of phonemes to obtain one or more acoustic representations, wherein the one or more sequences of phonemes are generated from a list of expected responses to the issued verbal prompt;

compare the acoustic input from the user to the one or more acoustic representations to determine an acoustic channel characterization and/or speaker class; and

adjust one or more speech recognition parameters based on the comparison, wherein the adjustment comprises an application of feature space mapping to the acoustic input, and further wherein the one or more adjusted speech recognition parameters are used to adapt a speech recognition module of a speech recognition system to use an acoustic model that is consistent with the acoustic channel characterization and/or speaker class so that the selected acoustic model is used for decoding subsequent acoustic input provided by the user as the conversation progresses.

9. The article of claim 8, wherein the comparison comprises a performance of a channel estimation on the acoustic input.

10. The article of claim 8, wherein the comparison comprises a performance of a spectral adaptation on the acoustic input.

11. The article of claim 8, wherein the comparison comprises a performance of a voice print analysis on the acoustic input.

12. The article of claim 8, wherein the comparison comprises a performance of a variable template matching on the acoustic input.

13. The article of claim 8, wherein the adjustment comprises a detection of a class of speaker based on the comparison results.

14. The article of claim 13, wherein the adjustment further comprises a selection of an acoustic model for the detected class of speaker.

15. The article of claim 8, wherein the adjustment comprises an application of feature space mapping to the acoustic input.

16. The article of claim 8, wherein the issued verbal prompt is selected from a database.

17. The article of claim 8, wherein the processing of the one or more sequences of phonemes comprises a generation of one or more sequences of voice frequency estimates in a given format.