Distributed voice user interface

• US 8,078,469 B2
• Filed: 01/22/2002
• Issued: 12/13/2011
• Est. Priority Date: 04/12/1999
• Status: Expired due to Fees

• Current Assignee: Intellectual Ventures I LLC (Intellectual Ventures LLC)
• Original Assignee: Ben Franklin Patent Holding LLC (Intellectual Ventures LLC)
• Inventors: White, George M., Buteau, James J., Shires, Glen E., Surace, Kevin J., Markman, Steven
• Primary Examiner(s): Lerner, Martin
• Application Number:
  US10/057,523
• Publication Number:
  US 20020072918A1
• Time in Patent Office: 3,612 Days
• Field of Search: 704/251, 704/252, 704/258, 704/270, 704/270.1, 704/275, 704/243, 704/244, 704/250, 704/255, 379/88.01, 379/88.16
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A distributed voice user interface system includes a local device which receives speech input issued from a user. Such speech input may specify a command or a request by the user. The local device performs preliminary processing of the speech input and determines whether it is able to respond to the command or request by itself. If not, the local device initiates communication with a remote system for further processing of the speech input.

Claims

1. A system for providing a distributed voice interface to a device, comprising:

a transceiver configured to receive input from the device via a communication network, wherein the input is the result of preliminary signal processing comprising keyword detection by the device prior to receipt of the input at the transceiver;

a memory configured to store an acoustic model of the input; and

a processing module coupled to the transceiver and configured to perform speech recognition on the received input based at least in part on a previously stored acoustic model in order to recognize a command,

wherein the transceiver is further configured to transmit data to the device, responsive to the command, via the communication network using communication channels comprising;

a high bandwidth communication channel configured to transmit data supporting audio or video output at the device, and

a low bandwidth communication channel configured to transmit data supporting control signals for operation of a primary functionality component of the device, and

wherein the data comprises audio data generated to be consistent with audio data generated by the device based on a type of the device.

2. The system of claim 1, wherein the data includes video data.

3. The system of claim 1, wherein the data includes audio data.

4. The system of claim 1, wherein the data include a text message.

5. The system of claim 1, wherein the input received from the device is not capable of being processed by the device.

6. The system of claim 1, wherein the processing module is further configured to retrieve remote data in response to the input received from the device.

7. The system of claim 1, the processing module further configured to:

update or modify the keyword detection based at least in part on words within the input; and

update the previously stored acoustic model based at least in part on the input.

8. A method for providing a distributed voice interface comprising:

receiving an audio input comprising results from preliminary signal processing, the preliminary signal processing comprising keyword detection on a speech input;

storing an acoustic model of the audio input;

performing speech recognition on the received audio input, based at least in part on a previously stored acoustic model in order to recognize a command; and

transmitting data to a device over a network, responsive to the command, using communication channels comprising;

a high bandwidth communication channel configured to transmit data supporting audio or video output at the device, and

a low bandwidth communication channel configured to transmit data supporting control signals for operation of a primary functionality component of the device,

wherein the data comprises audio data generated to be consistent with audio data generated by the device based on a type of the device.

9. The method of claim 8, wherein the data includes video data.

10. The method of claim 8, wherein the data includes audio data.

11. The method of claim 8, wherein the data include a text message.

12. The method of claim 8, wherein the input received from the device is not capable of being processed by the device.

13. The method of claim 8, further comprising:

retrieving remote data in response to the input received from the device.

14. The method of claim 8, further comprising:

updating or modifying the keyword detection based at least in part on words within the audio input; and

updating the previously stored acoustic model based at least in part on the audio input.

15. A computer-readable medium having computer program logic recorded thereon, execution of which, by a computing device, causes the computing device to perform operations comprising:

receiving an audio input from a device via a communication network, the audio input based at least in part on speech input, wherein the audio input is the result of preliminary signal processing comprising keyword detection by the device prior to receipt of the audio input;

performing speech recognition on the received audio input based at least in part on a previously stored acoustic model in order to recognize a command; and

transmitting data to the device, responsive to the command, via the communication network using communication channels comprising;

a high bandwidth communication channel configured to transmit data supporting audio or video output at the device, and

a low bandwidth communication channel configured to transmit data supporting control signals for operation of a primary functionality component of the device,

wherein the data comprises audio data generated to be consistent with audio data generated by the device based on a type of the device.

16. The computer program product of claim 15, wherein the data includes video data.

17. The computer program product of claim 15, wherein the data includes audio data.

18. The computer program product of claim 15, wherein the data include a text message.

19. The computer-readable medium of claim 15, wherein the input received from the device is not capable of being processed by the device.

20. The computer-readable medium of claim 15, further comprising:

retrieving remote data in response to the input received from the device.

21. The computer-readable medium of claim 15, further comprising:

;

updating or modifying the keyword detection based at least in part on words within the audio input; and

updating the previously stored acoustic model based at least in part on the audio input.

22. A system for providing a distributed voice interface to a device, comprising:

transceiver means for receiving input from the device via a communication network, wherein the input is the result of preliminary signal processing comprising keyword detection by the device prior to receipt of the input at the transceiver means;

memory means for storing an acoustic model of the input; and

processing means for performing speech recognition on the received input based at least in part on a previously stored acoustic model in order to recognize a command,

wherein the transceiver means are further for transmitting data to the device, responsive to the command, via the communication network using communication channels comprising;

a high bandwidth communication channel configured to transmit data supporting audio or video output at the device, and

a low bandwidth communication channel configured to transmit data supporting control signals for operation of a primary functionality component of the device,

wherein the data comprises audio data generated to be consistent with audio data generated by the device based on a type of the device.

23. The system of claim 22, the processing means further for:

updating or modifying the keyword detection based at least in part on words within the input; and

updating the previously stored acoustic model based at least in part on the input.

24. A system for providing a distributed voice interface to a device, comprising:

a communication module configured to receive input from the device via a communication network, wherein the input is the result of preliminary signal processing comprising keyword detection by the device prior to receipt of the input at the communication module;

a memory module configured to store an acoustic model of the input; and

a processing module coupled to the communication module and configured to perform speech recognition on the received input based at least in part on a previously stored acoustic model in order to recognize a command,

wherein the communication module is further configured to transmit data to the device, responsive to the command, via the communication network using communication channels comprising;

a high bandwidth communication channel configured to transmit data supporting audio or video output at the device, and

a low bandwidth communication channel configured to transmit data supporting control signals for operation of a primary functionality component of the device,

wherein the data comprises audio data generated to be consistent with audio data generated by the device based on a type of the device.

25. The system of claim 24, the processing module further configured to:

update or modify the keyword detection based at least in part on words within the input; and

update the previously stored acoustic model based at least in part on the input.