Performing speech recognition over a network and using speech recognition results

• US 8,401,846 B1
• Filed: 02/22/2012
• Issued: 03/19/2013
• 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): MCFADDEN, SUSAN IRIS
• Application Number:
  US13/401,932
• Time in Patent Office: 391 Days
• Field of Search: 704/231
• US Class Current: 704/231
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

Systems, methods and apparatus for generating, distributing, and using speech recognition models. 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. 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, by a client device, speech data;

initiating, by the client device, a local voice dialing operation using the speech data, wherein initiating the local voice dialing operation comprises;

extracting, by a feature extraction module on the client device, one or more features from the speech data, and

performing, by a speech recognition module on the client device, a speech recognition operation on the extracted features using one or more locally stored speech recognition models;

determining, by the client device, that the local voice dialing operation was unsuccessful;

in response to determining that the local voice dialing operation was unsuccessful, transmitting, by the client device and to a remote speech processing system, a request to perform a remote voice dialing operation, wherein the request includes the speech data or the extracted features; and

receiving, by the client device and from the remote speech processing system, a response to the request.

2. The method of claim 1, wherein the local voice dialing operation comprises an operation for attempting voice dialing without having to contact the remote speech processing system.

3. The method of claim 1, wherein determining that the local voice dialing operation was unsuccessful comprises determining that a name was not recognized as a result of the speech recognition operation.

4. The method of claim 1, wherein determining that the local voice dialing operation was unsuccessful comprises determining that the client device did not determine a telephone number to be dialed.

5. The method of claim 1, wherein the request to perform the remote voice dialing operation includes data indicating that the local voice dialing operation was unsuccessful.

6. The method of claim 1, wherein the request to perform the remote voice dialing operation includes data identifying a user of the mobile device.

7. The method of claim 1, wherein the request to perform the remote voice dialing operation includes the speech data and the extracted features.

8. The method of claim 1, comprising determining, by the client device, whether the response from the remote speech processing system includes a contact telephone number.

9. The method of claim 8, comprising displaying, by the client device, a message to the user of the client device when the response does not include a telephone number, wherein the message indicates a result of the remote voice dialing operation.

10. The method of claim 8, comprising dialing, by the client device, the contact telephone number when the response includes the contact telephone number.

11. The method of claim 1, wherein the request identifies an additional remote speech processing system associated with the identified user, that the remote speech processing system can use to support the remote voice dialing operation.

12. A system comprising:

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

receiving, by a client device, speech data;

initiating, by the client device, a local voice dialing operation using the speech data, wherein initiating the local voice dialing operation comprises;

extracting, by a feature extraction module on the client device, one or more features from the speech data, and

performing, by a speech recognition module on the client device, a speech recognition operation on the extracted features using one or more locally stored speech recognition models;

determining, by the client device, that the local voice dialing operation was unsuccessful;

in response to determining that the local voice dialing operation was unsuccessful, transmitting, by the client device and to a remote speech processing system, a request to perform a remote voice dialing operation, wherein the request includes the speech data or the extracted features; and

receiving, by the client device and from the remote speech processing system, a response to the request.

13. The system of claim 12, wherein the local voice dialing operation comprises an operation for attempting voice dialing without having to contact the remote speech processing system.

14. The system of claim 12, wherein determining that the local voice dialing operation was unsuccessful comprises determining that a name was not recognized as a result of the speech recognition operation.

15. The system of claim 12, wherein determining that the local voice dialing operation was unsuccessful comprises determining that the client device did not determine a telephone number to be dialed.

16. The system of claim 12, wherein the request to perform the remote voice dialing operation includes data indicating that the local voice dialing operation was unsuccessful.

17. The system of claim 12, wherein the request to perform the remote voice dialing operation includes data identifying a user of the mobile device.

18. The system of claim 12, wherein the request to perform the remote voice dialing operation includes the speech data and the extracted features.

19. The system of claim 12, wherein the operations comprise determining, by the client device, whether the response from the remote speech processing system includes a contact telephone number.

20. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, if executed, cause the one or more computers to perform operations comprising:

receiving, by a client device, speech data;

initiating, by the client device, a local voice dialing operation using the speech data, wherein initiating the local voice dialing operation comprises;

extracting, by a feature extraction module on the client device, one or more features from the speech data, and

performing, by a speech recognition module on the client device, a speech recognition operation on the extracted features using one or more locally stored speech recognition models;

determining, by the client device, that the local voice dialing operation was unsuccessful;

in response to determining that the local voice dialing operation was unsuccessful, transmitting, by the client device and to a remote speech processing system, a request to perform a remote voice dialing operation, wherein the request includes the speech data or the extracted features; and

receiving, by the client device and from the remote speech processing system, a response to the request.