Recognizing accented speech

• US 9,734,819 B2
• Filed: 02/21/2013
• Issued: 08/15/2017
• Est. Priority Date: 02/21/2013
• Status: Active Grant

• Current Assignee: Google Technology Holdings LLC (Alphabet Inc.)
• Original Assignee: Google Technology Holdings LLC (Alphabet Inc.)
• Inventors: Gray, Kristin A.
• Primary Examiner(s): Ky, Kevin
• Application Number:
  US13/772,373
• Publication Number:
  US 20140236595A1
• Time in Patent Office: 1,636 Days
• Field of Search: None
• CPC Class Codes: G06F 40/174 Form filling; Merging
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/01 Assessment or evaluation of speech recognition systems
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/1807 using prosody or stress
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/0635 updating or merging of old and new templates; Mean values; Weighting
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology

Abstract

Techniques (300, 400, 500) and apparatuses (100, 200, 700) for recognizing accented speech are described. In some embodiments, an accent module recognizes accented speech using an accent library based on device data, uses different speech recognition correction levels based on an application field into which recognized words are set to be provided, or updates an accent library based on corrections made to incorrectly recognized speech.

Claims

1. A computer-implemented method comprising:

receiving, from a user, an utterance that was spoken while focus is set on a field of a form;

determining, from among one or more different field types, a field type associated with the field;

determining, from among different, predefined levels of speech recognition accuracy and from among different, predefined levels of speech recognition latency, a predefined level of speech recognition accuracy and a predefined level of speech recognition latency that are indicated as acceptable for the field type;

selecting, based at least on the predefined level of speech recognition accuracy and a predefined level of speech recognition latency that are indicated as acceptable for the field type, (i) one or more accent libraries that each include phonemes for different pronunciations for words of a language and (ii) a level of correction for a speech recognition system to apply to a transcription;

obtaining, from the speech recognition system, the transcription of the utterance that is generated by the speech recognition system; and

providing the transcription of the utterance in the field of the form.

2. The method of claim 1, comprising:

selecting the one or more accent libraries based on personal data that is associated with the user and is stored on a computing device that receives the utterance.

3. The method of claim 2, wherein selecting the one or more accent libraries based on personal data that is associated with the user and is stored on a computing device that receives the utterance comprises:

identifying countries of addresses stored in an address book; and

selecting the one or more accent libraries based on the countries and on a current location of the computing device.

4. The method of claim 1, wherein the one or more accent libraries are associated with a default language of the computing device.

5. The method of claim 1, wherein the speech recognition system generates the transcription of the utterance without accessing a linguistic library.

6. The method of claim 1, wherein obtaining, from the speech recognition system, the transcription of the utterance that is generated by the speech recognition system comprises:

obtaining, from the speech recognition system, the transcription of the utterance that is generated by the speech recognition system using the one or more accent libraries.

7. 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, from a user, an utterance that was spoken while focus is set on a field of a form;

determining, from among one or more different field types, a field type associated with the field;

determining, from among different, predefined levels of speech recognition accuracy and from among different, predefined levels of speech recognition latency, a predefined level of speech recognition accuracy and a predefined level of speech recognition latency that are indicated as acceptable for the field type;

selecting, based at least on the predefined level of speech recognition accuracy and a predefined level of speech recognition latency that are indicated as acceptable for the field type, (i) one or more accent libraries that each include phonemes for different pronunciations for words of a language and (ii) a level of correction for a speech recognition system to apply to a transcription;

obtaining, from the speech recognition system, the transcription of the utterance that is generated by the speech recognition system; and

providing the transcription of the utterance in the field of the form.

8. The system of claim 7, wherein the operations further comprise:

selecting the one or more accent libraries based on personal data that is associated with the user and is stored on a computing device that receives the utterance.

9. The system of claim 8, wherein selecting the one or more accent libraries based on personal data that is associated with the user and is stored on a computing device that receives the utterance comprises:

identifying countries of addresses stored in an address book; and

selecting the one or more accent libraries based on the countries and on a current location of the computing device.

10. The system of claim 7, wherein the one or more accent libraries are associated with a default language of the computing device.

11. The system of claim 7, wherein the speech recognition system generates the transcription of the utterance without accessing a linguistic library.

12. The system of claim 7, wherein obtaining, from the speech recognition system, the transcription of the utterance that is generated by the speech recognition system comprises:

obtaining, from the speech recognition system, the transcription of the utterance that is generated by the speech recognition system using the one or more accent libraries.

13. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving, from a user, an utterance that was spoken while focus is set on a field of a form;

determining, from among one or more different field types, a field type associated with the field;

determining, from among different, predefined levels of speech recognition accuracy and from among different, predefined levels of speech recognition latency, a predefined level of speech recognition accuracy and a predefined level of speech recognition latency that are indicated as acceptable for the field type;

selecting, based at least on the predefined level of speech recognition accuracy and a predefined level of speech recognition latency that are indicated as acceptable for the field type, (i) one or more accent libraries that each include phonemes for different pronunciations for words of a language and (ii) a level of correction for a speech recognition system to apply to a transcription;

obtaining, from the speech recognition system, the transcription of the utterance that is generated by the speech recognition system; and

providing the transcription of the utterance in the field of the form.

14. The medium of claim 13, comprising:

selecting the one or more accent libraries based on personal data that is associated with the user and is stored on a computing device that receives the utterance.

15. The medium of claim 14, wherein selecting the one or more accent libraries based on personal data that is associated with the user and is stored on a computing device that receives the utterance comprises:

identifying countries of addresses stored in an address book; and

selecting the one or more accent libraries based on the countries and on a current location of the computing device.

16. The medium of claim 13, wherein the one or more accent libraries are associated with a default language of the computing device.

17. The medium of claim 13, wherein the speech recognition system generates the transcription of the utterance without accessing a linguistic library.

18. The medium of claim 13, wherein obtaining, from the speech recognition system, the transcription of the utterance that is generated by the speech recognition system comprises:

obtaining, from the speech recognition system, the transcription of the utterance that is generated by the speech recognition system using the one or more accent libraries.