System and method of performing automatic speech recognition using local private data

• US 9,905,228 B2
• Filed: 05/26/2017
• Issued: 02/27/2018
• Est. Priority Date: 10/29/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Thomson, David, Johnston, Michael J., Rangarajan Sridhar, Vivek Kumar
• Primary Examiner(s): Armstrong, Angela A
• Application Number:
  US15/606,477
• Publication Number:
  US 20170263253A1
• Time in Patent Office: 277 Days
• 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 2015/228 of application context

Abstract

A method of providing hybrid speech recognition between a local embedded speech recognition system and a remote speech recognition system relates to receiving speech from a user at a device communicating with a remote speech recognition system. The system recognizes a first part of speech by performing a first recognition of the first part of the speech with the embedded speech recognition system that accesses private user data, wherein the private user data is not available to the remote speech recognition system. The system recognizes the second part of the speech by performing a second recognition of the second part of the speech with the remote speech recognition system. The final recognition result is a combination of these two recognition processes. The private data can be such local information as a user location, a playlist, frequently dialed numbers or texted people, user contact list information, and so forth.

Claims

1. A method comprising:

receiving, on a device, text as part of a message, a placeholder within the text and audio, wherein the device comprises an embedded speech recognition system that accesses private user data on the device;

receiving one of a garbage model, phonemic language model, a language model according to a standard list, and a language model built on the private user data to yield a received component;

determining a privacy level of the private user data;

recognizing the audio using the received component, the embedded speech recognition system and by accessing the private user data according to the privacy level to yield a recognition result; and

replacing the placeholder with the recognition result in the text to yield an updated message.

2. The method of claim 1, wherein the private user data is not available to a remote speech recognition system in communication with the device.

3. The method of claim 1, further comprising:

identifying a location of the device.

4. The method of claim 3, further comprising:

determining a privacy level of the private user data according to the location of the device.

5. The method of claim 1, wherein individual names from a user contact list are from the private user data.

6. The method of claim 1, wherein the private user data comprises one of data in a user contact list, frequently dialed phone numbers, frequently used texted names, data associated with a user location, data associated with a playlist, user history, and multiple hypothesis associated with private information.

7. A computer-readable storage device storing instructions which, when executed by a processor, cause the processor to perform operations comprising:

receiving text as part of a message, a placeholder within the text and audio, wherein the device comprises an embedded speech recognition system that accesses private user data on a computing device;

receiving one of a garbage model, phonemic language model, a language model according to a standard list, and a language model built on the private user data to yield a received component;

determining a privacy level of the private user data;

recognizing the audio using the received component, the embedded speech recognition system and by accessing the private user data according to the privacy level to yield a recognition result; and

replacing the placeholder with the recognition result in the text to yield an updated message.

8. The computer-readable storage device of claim 7, wherein the private user data is not available to a remote speech recognition system in communication with the computing device.

9. The computer-readable storage device of claim 7, wherein the computer-readable storage device stores additional instructions which, when executed by the processor, cause the processor to perform operations further comprising:

identifying a location of the computing device.

10. The computer-readable storage device of claim 9, wherein the computer-readable storage device stores additional instructions which, when executed by the processor, cause the processor to perform operations further comprising:

determining a privacy level of the private user data according to the location of the computing device.

11. The computer-readable storage device of claim 7, wherein individual names from a user contact list are from the private user data.

12. The computer-readable storage device of claim 7, wherein the private user data comprises one of data in a user contact list, frequently dialed phone numbers, frequently used texted names, data associated with a user location, data associated with a playlist, user history, and multiple hypothesis associated with private information.

13. A system comprising:

a processor; and

a computer-readable storage medium storing instructions which, when executed by the processor, cause the processor to perform operations comprising;

receiving text as part of a message, a placeholder within the text and audio, wherein the system comprises an embedded speech recognition system that accesses private user data on the system;

receiving one of a garbage model, phonemic language model, a language model according to a standard list, and a language model built on the private user data to yield a received component;

determining a privacy level of the private user data;

recognizing the audio using the received component, the embedded speech recognition system and by accessing the private user data according to the privacy level to yield a recognition result; and

replacing the placeholder with the recognition result in the text to yield an updated message.

14. The system of claim 13, wherein the private user data is not available to a remote speech recognition system in communication with the system.

15. The system of claim 13, wherein the computer-readable storage medium stores additional instructions which, when executed by the processor, cause the processor to perform operations further comprising:

identifying a location of the system.

16. The system of claim 15, wherein the computer-readable storage medium stores additional instructions which, when executed by the processor, cause the processor to perform operations further comprising:

determining a privacy level of the private user data according to the location of the system.

17. The system of claim 13, wherein individual names from a user contact list are from the private user data.

18. The system of claim 13, wherein the private user data comprises one of data in a user contact list, frequently dialed phone numbers, frequently used texted names, data associated with a user location, data associated with a playlist, user history, and multiple hypothesis associated with private information.