Methods and apparatus for generating, updating and distributing speech recognition models

• US 8,818,809 B2
• Filed: 06/20/2013
• Issued: 08/26/2014
• Est. Priority Date: 11/30/2000
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Reding, Craig L., Levas, Suzi
• Primary Examiner(s): Han, Qi
• Application Number:
  US13/922,602
• Publication Number:
  US 20130279665A1
• Time in Patent Office: 432 Days
• Field of Search: 704/244, 704/231, 704/235, 704/251, 704/243, 704/270
• US Class Current: 704/244
• CPC Class Codes: G10L 15/00 Speech recognition G10L17/00 takes precedence
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

Techniques for generating, distributing, and using speech recognition models are described. A shared speech processing facility is used to support speech recognition for a wide variety of devices with limited capabilities including business computer systems, personal data assistants, etc., which are coupled to the speech processing facility via a communications channel, e.g., the Internet. Devices with audio capture capability record and transmit to the speech processing facility, via the Internet, digitized speech and receive speech processing services, e.g., speech recognition model generation and/or speech recognition services, in response. The Internet is used to return speech recognition models and/or information identifying recognized words or phrases. Thus, the speech processing facility can be used to provide speech recognition capabilities to devices without such capabilities and/or to augment a device'"'"'s speech processing capability. Voice dialing, telephone control and/or other services are provided by the speech processing facility in response to speech recognition results.

Claims

1. A computer-implemented method comprising:

receiving, from a mobile device, a request to update at least a portion of an existing speech recognition model corresponding to a particular term, the request including (i) a recording of a user of the mobile device speaking the particular term, or (ii) a set of features extracted from the recording of the user of the mobile device speaking the particular term;

determining a speech recognition model type of the existing speech recognition model, wherein the speech recognition model type comprises a speaker-dependent speech recognition model type or a speaker-independent speech recognition model type;

in response to determining the speech recognition model type of the existing speech recognition model, generating an updated speech recognition model of the determined speech recognition model type of the existing speech recognition model; and

transmitting the updated speech recognition model corresponding to the particular term to the mobile device, as a replacement for the speech recognition model corresponding to the particular term.

2. The method of claim 1, wherein transmitting the updated speech recognition model corresponding to the particular term to the mobile device, as a replacement for the speech recognition model corresponding to the particular term, comprises:

determining that a selected time interval has passed; and

based on determining that the selected time interval has passed, transmitting the updated speech recognition model corresponding to the particular term to the mobile device.

3. The method of claim 1, wherein transmitting the updated speech recognition model corresponding to the particular term to the mobile device, as a replacement for the speech recognition model corresponding to the particular term, comprises:

based on generating the updated speech recognition model corresponding to the particular term based on the request, determining a second mobile device that uses the existing speech recognition model; and

transmitting the updated speech recognition model corresponding to the particular term to the second mobile device, as a replacement for the speech recognition model corresponding to the particular term.

4. The method of claim 3, wherein determining a second mobile device that uses the existing speech recognition model comprises:

determining that the second mobile device was associated, before receiving the request, with the existing speech recognition model.

5. The method of claim 1, wherein the existing speech recognition model comprises a speaker-dependent speech recognition model associated with the mobile device, comprising:

generating an update for a speaker-independent speech recognition model associated with a second mobile device based on the request; and

transmitting the speaker-independent speech recognition model to the second mobile device.

6. 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 mobile device, a request to update at least a portion of an existing speech recognition model corresponding to a particular term, the request including (i) a recording of a user of the mobile device speaking the particular term, or (ii) a set of features extracted from the recording of the user of the mobile device speaking the particular term;

determining a speech recognition model type of the existing speech recognition model, wherein the speech recognition model type comprises a speaker-dependent speech recognition model type or a speaker-independent speech recognition model type;

in response to determining the speech recognition model type of the existing speech recognition model, generating an updated speech recognition model of the determined speech recognition model type of the existing speech recognition model; and

transmitting the updated speech recognition model corresponding to the particular term to the mobile device, as a replacement for the speech recognition model corresponding to the particular term.

7. The system of claim 6, wherein transmitting the updated speech recognition model corresponding to the particular term to the mobile device, as a replacement for the speech recognition model corresponding to the particular term, comprises:

determining that a selected time interval has passed; and

based on determining that the selected time interval has passed, transmitting the updated speech recognition model corresponding to the particular term to the mobile device.

8. The system of claim 6, wherein transmitting the updated speech recognition model corresponding to the particular term to the mobile device, as a replacement for the speech recognition model corresponding to the particular term, comprises:

based on generating the updated speech recognition model corresponding to the particular term based on the request, determining a second mobile device that uses the existing speech recognition model; and

transmitting the updated speech recognition model corresponding to the particular term to the second mobile device, as a replacement for the speech recognition model corresponding to the particular term.

9. The system of claim 8, wherein determining a second mobile device that uses the existing speech recognition model comprises:

determining that the second mobile device was associated, before receiving the request, with the existing speech recognition model.

10. The system of claim 6, wherein the existing speech recognition model comprises a speaker-dependent speech recognition model associated with the mobile device, the operations comprising:

generating an update for a speaker-independent speech recognition model associated with a second mobile device based on the request; and

transmitting the speaker-independent speech recognition model to the second mobile device.

11. 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 mobile device, a request to update at least a portion of an existing speech recognition model corresponding to a particular term, the request including (i) a recording of a user of the mobile device speaking the particular term, or (ii) a set of features extracted from the recording of the user of the mobile device speaking the particular term;

determining a speech recognition model type of the existing speech recognition model, wherein the speech recognition model type comprises a speaker-dependent speech recognition model type or a speaker-independent speech recognition model type;

in response to determining the speech recognition model type of the existing speech recognition model, generating an updated speech recognition model of the determined speech recognition model type of the existing speech recognition model; and

transmitting the updated speech recognition model corresponding to the particular term to the mobile device, as a replacement for the speech recognition model corresponding to the particular term.

12. The medium of claim 11, wherein transmitting the updated speech recognition model corresponding to the particular term to the mobile device, as a replacement for the speech recognition model corresponding to the particular term, comprises:

determining that a selected time interval has passed; and

based on determining that the selected time interval has passed, transmitting the updated speech recognition model corresponding to the particular term to the mobile device.

13. The medium of claim 11, wherein transmitting the updated speech recognition model corresponding to the particular term to the mobile device, as a replacement for the speech recognition model corresponding to the particular term, comprises:

based on generating the updated speech recognition model corresponding to the particular term based on the request, determining a second mobile device that uses the existing speech recognition model; and

transmitting the updated speech recognition model corresponding to the particular term to the second mobile device, as a replacement for the speech recognition model corresponding to the particular term.

14. The medium of claim 13, wherein determining a second mobile device that uses the existing speech recognition model comprises:

determining that the second mobile device was associated, before receiving the request, with the existing speech recognition model.