DYNAMICALLY BIASING LANGUAGE MODELS

• US 20160104482A1
• Filed: 10/28/2014
• Published: 04/14/2016
• Est. Priority Date: 10/08/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Aleksic, Petar, Mengibar, Pedro J. Moreno
• Granted Patent: US 9,502,032 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: G10L 19/00 Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis in musical instruments G10H

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition. In one aspect, a method comprises receiving audio data encoding one or more utterances; performing a first speech recognition on the audio data; identifying a context based on the first speech recognition; performing a second speech recognition on the audio data that is biased towards the context; and providing an output of the second speech recognition.

Claims

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

receiving audio data encoding one or more utterances;

generating a recognition lattice of the one or more utterances by performing speech recognition on the audio data using a first pass speech recognizer;

determining a specific context for the one or more utterances based on the recognition lattice;

in response to determining that the recognition lattice defines the specific context, generating a transcription of the one or more utterances by performing speech recognition on the audio data using a second pass speech recognizer biased towards the specific context defined by the recognition lattice; and

providing an output of the transcription of the one or more utterances.

2. The method of claim 1, wherein generating the recognition lattice comprises generating one or more text phrases that acoustically match the utterances according to a first language model.

3. The method of claim 2, wherein determining that the recognition lattice defines the specific context for the utterances comprises performing semantic analysis on the text phrases.

4. The method of claim 2, wherein determining that the recognition lattice defines the specific context comprises determining that at least a first text phrase matches a first title of a first context language model of a plurality of context language models, wherein the first context language model comprises a biasing language model for the specific context.

5. The method of claim 2, wherein determining that the recognition lattice defines the specific context comprises supplying the recognition lattice to a classifier trained using recognition lattice data.

6. The method of claim 1, wherein performing speech recognition on the audio data using a second pass speech recognizer biased towards the specific context defined by the recognition lattice comprises:

selecting a context language model for the specific context, the context language model specifying a plurality of potential output phrases associated with the specific context, wherein the number of potential output phrases is fewer than a number of potential output phrases of a general language model;

supplying the context language model, the general language model, and the audio data to an automatic speech recognition engine.

7. The method of claim 6, comprising supplying respective weights for the context language model and the general language model to the automatic speech recognition engine based on the recognition lattice.

8. The method of claim 6, wherein supplying the context language model and the general language model to the automatic speech recognition engine comprises combining the context language model and the general language model into a combined language model and supplying the combined language model to the automatic speech recognition engine.

9. The method of claim 1, wherein performing speech recognition on the audio data using a first pass speech recognizer comprises biasing the first pass speech recognizer.

10. The method of claim 1, comprising determining that the recognition lattice defines an additional context for the utterances, wherein performing speech recognition on the audio data using the second pass speech recognizer biased towards both the specific context and the additional context.

11. 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 audio data encoding one or more utterances;

generating a recognition lattice of the one or more utterances by performing speech recognition on the audio data using a first pass speech recognizer;

determining a specific context for the one or more utterances based on the recognition lattice;

in response to determining that the recognition lattice defines the specific context, generating a transcription of the one or more utterances by performing speech recognition on the audio data using a second pass speech recognizer biased towards the specific context defined by the recognition lattice; and

providing an output of the transcription of the one or more utterances.

12. The system of claim 11, wherein generating the recognition lattice comprises generating one or more text phrases that acoustically match the utterances according to a first language model.

13. The system of claim 12, wherein determining that the recognition lattice defines the specific context for the utterances comprises performing semantic analysis on the text phrases.

14. The system of claim 12, wherein determining that the recognition lattice defines the specific context comprises determining that at least a first text phrase matches a first title of a first context language model of a plurality of context language models, wherein the first context language model comprises a biasing language model for the specific context.

15. The system of claim 12, wherein determining that the recognition lattice defines the specific context comprises supplying the recognition lattice to a classifier trained using recognition lattice data.

16. The system of claim 11, wherein performing speech recognition on the audio data using a second pass speech recognizer biased towards the specific context defined by the recognition lattice comprises:

selecting a context language model for the specific context, the context language model specifying a plurality of potential output phrases associated with the specific context, wherein the number of potential output phrases is fewer than a number of potential output phrases of a general language model;

supplying the context language model, the general language model, and the audio data to an automatic speech recognition engine.

17. The system of claim 16, the operations comprising supplying respective weights for the context language model and the general language model to the automatic speech recognition engine based on the recognition lattice.

18. The system of claim 16, wherein supplying the context language model and the general language model to the automatic speech recognition engine comprises combining the context language model and the general language model into a combined language model and supplying the combined language model to the automatic speech recognition engine.

19. The system of claim 16, wherein performing speech recognition on the audio data using a first pass speech recognizer comprises biasing the first pass speech recognizer.

20. The system of claim 11, the operations comprising determining that the recognition lattice defines an additional context for the utterances, wherein performing speech recognition on the audio data using the second pass speech recognizer biased towards both the specific context and the additional context.

21. A system of one or more computers configured to perform operations comprising:

receiving audio data encoding one or more utterances;

performing a first speech recognition on the audio data;

identifying a context based on the first speech recognition;

performing a second speech recognition on the audio data that is biased towards the context; and

providing an output of the second speech recognition.