CACHING SPEECH RECOGNITION SCORES

• US 20150371631A1
• Filed: 06/23/2014
• Published: 12/24/2015
• Est. Priority Date: 06/23/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Weinstein, Eugene, Kumar, Sanjiv, Moreno, Ignacio L., Senior, Andrew W., Bhat, Nikhil Prasad
• Granted Patent: US 9,858,922 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/285 Memory allocation or algorithm optimisation to reduce hardware requirements

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for caching speech recognition scores. In some implementations, one or more values comprising data about an utterance are received. An index value is determined for the one or more values. An acoustic model score for the one or more received values is selected, from a cache of acoustic model scores that were computed before receiving the one or more values, based on the index value. A transcription for the utterance is determined using the selected acoustic model score.

Claims

1. A method performed by one or more computers, the method comprising:

receiving one or more values comprising data about an utterance;

determining an index value for the one or more values;

selecting an acoustic model score based on the index value, wherein the acoustic model score is selected from a cache of acoustic model scores that were computed before receiving the one or more values; and

determining a transcription for the utterance using the selected acoustic model score.

2. The method of claim 1, wherein generating the index value comprises generating a hash value for the one or more values using a locality sensitive hash function.

3. The method of claim 2, wherein selecting the acoustic model score for the received one or more values comprises selecting an acoustic model score previously generated for a set of values that matches the received one or more values.

4. The method of claim 2, wherein selecting the acoustic model score for the received one or more values comprises selecting an acoustic model score previously generated for a set of values that does not exactly match the received one or more values, the acoustic model score approximating an acoustic model score for the received one or more values.

5. The method of claim 1, wherein the one or more values comprise information derived from a particular speech frame and information derived from contextual speech frames occurring before or after the particular frame;

and

wherein determining the index value for the one or more values comprises determining the hash value for the particular speech frame based on the information derived from a particular speech frame and information derived from the contextual speech frames occurring before or after the particular frame.

6. The method of claim 5, wherein selecting the acoustic model score comprises selecting an acoustic model score indicating a likelihood that the particular speech frame is an occurrence of a particular phonetic unit in the utterance.

7. The method of claim 1, further comprising selecting multiple acoustic model scores from the cache based on the index value, each of the multiple acoustic model scores indicating a likelihood that the utterance includes a different phonetic unit in a portion corresponding to the one or more values.

8. The method of claim 1, wherein receiving the one or more values comprises, receiving the one or more values from a client device over a network;

wherein the method further comprises providing the transcription to the client device over the network.

9. The method of claim 1, wherein the one or more values comprise results of compressing speech features for the utterance using vector quantization.

10. A system comprising:

one or more computers; and

one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving one or more values comprising data about an utterance;

determining an index value for the one or more values;

selecting an acoustic model score based on the index value, wherein the acoustic model score is selected from a cache of acoustic model scores that were computed before receiving the one or more values; and

determining a transcription for the utterance using the selected acoustic model score.

11. The system of claim 10, wherein generating the index value comprises generating a hash value for the one or more values using a locality sensitive hash function.

12. The system of claim 11, wherein selecting the acoustic model score for the received one or more values comprises selecting an acoustic model score previously generated for a set of values that matches the received one or more values.

13. The system of claim 11, wherein selecting the acoustic model score for the received one or more values comprises selecting an acoustic model score previously generated for a set of values that does not exactly match the received one or more values, the acoustic model score approximating an acoustic model score for the received one or more values.

14. The system of claim 10, wherein the one or more values comprise information derived from a particular speech frame and information derived from contextual speech frames occurring before or after the particular frame;

and

wherein determining the index value for the one or more values comprises determining the hash value for the particular speech frame based on the information derived from a particular speech frame and information derived from the contextual speech frames occurring before or after the particular frame.

15. The system of claim 14, wherein selecting the acoustic model score comprises selecting an acoustic model score indicating a likelihood that the particular speech frame is an occurrence of a particular phonetic unit in the utterance.

16. A computer storage device storing instructions that, when executed by a computer, cause the computer to perform operations comprising:

receiving one or more values comprising data about an utterance;

determining an index value for the one or more values;

selecting an acoustic model score based on the index value, wherein the acoustic model score is selected from a cache of acoustic model scores that were computed before receiving the one or more values; and

determining a transcription for the utterance using the selected acoustic model score.

17. The computer storage device of claim 16, wherein generating the index value comprises generating a hash value for the one or more values using a locality sensitive hash function.

18. The computer storage device of claim 17, wherein selecting the acoustic model score for the received one or more values comprises selecting an acoustic model score previously generated for a set of values that matches the received one or more values.

19. The computer storage device of claim 17, wherein selecting the acoustic model score for the received one or more values comprises selecting an acoustic model score previously generated for a set of values that does not exactly match the received one or more values, the acoustic model score approximating an acoustic model score for the received one or more values.

20. The computer storage device of claim 16, wherein the one or more values comprise information derived from a particular speech frame and information derived from contextual speech frames occurring before or after the particular frame;

and

wherein determining the index value for the one or more values comprises determining the hash value for the particular speech frame based on the information derived from a particular speech frame and information derived from the contextual speech frames occurring before or after the particular frame.