System and method for transmitting voice input from a remote location over a wireless data channel

• US 7,769,143 B2
• Filed: 10/30/2007
• Issued: 08/03/2010
• Est. Priority Date: 03/29/2001
• Status: Expired due to Fees

• Current Assignee: Intellisist, Inc. dba Spoken Communications (Avaya Incorporated)
• Original Assignee: Intellisist, Inc. dba Spoken Communications (Avaya Incorporated)
• Inventors: Odinak, Gilad
• Primary Examiner(s): Anwah, Olisa
• Application Number:
  US11/929,458
• Publication Number:
  US 20080140419A1
• Time in Patent Office: 1,008 Days
• Field of Search: 379/88.1, 379/406.01, 379/88.01, 379/406.03, 455/563, 704/270.1, 704/270, 704/231, 704/253, 704/246, 704/275, 704/248
• US Class Current: 379/88.01
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

A system and method for improving voice recognition processing at a server system that receives voice input from a remotely located user system. The user system includes a microphone, a processor that performs front-end voice recognition processing of the received user voice input, and a communication component configured to send the front-end processed user voice input to a destination wirelessly over a network. The server system includes a communication component configured to receive the sent front-end processed user voice input, and a processor configured to complete voice recognition processing of the sent front-end processed user voice input.

Claims

1. A method for digital signal manipulation, comprising:

receiving an acoustic analog signal at a user system;

converting the analog signal to a digital signal;

canceling noise from the digital signal to form a processed digital signal;

detecting user speech in the processed digital signal by evaluating change in amplitude sign of the processed digital signal;

detecting vehicle information associated with the user speech; and

if user speech is detected in the processed digital signal,

packaging the user speech into speech packets to form a packaged voice signal;

selecting a transmission format compatible with the packaged voice signal; and

transmitting the packaged voice signal and vehicle information to a server.

2. The method of claim 1, wherein digital signal noise comprises echoes.

3. The method of claim 1, wherein detecting user speech comprises evaluating rate of amplitude change in the processed digital signal.

4. The method of claim 1, further comprising:

matching the user speech of the voice signal with instructions stored in the server database; and

executing the instructions stored in the server database based on the user speech of the voice signal.

5. The method of claim 4, wherein matching the user speech at the server comprises statistical modeling and grammar analysis of the user speech.

6. The method of claim 1, wherein the user system is implemented in a vehicle.

7. The method of claim 1, wherein the packaged voice signal is transmitted to the server via wireless transmission.

8. The method of claim 1, further comprising:

receiving non-acoustic data at the user system; and

if user speech is not detected in the processed digital signal,

packaging the non-acoustic data into data packets to form a packaged data signal;

selecting a transmission format compatible with the packaged data signal; and

transmitting the packaged data signal to a server.

9. The method of claim 8, wherein the packaged data signal is transmitted to the server using a maximum possible bandwidth.

10. The method of claim 1, wherein if user speech is detected in the processed digital signal, further comprising:

evaluating the processed digital signal to determine whether data exist that enhances speech detection and matching at the server; and

if data from the processed digital signal exist to be transmitted to the server to enhance speech detection and matching at the server,

packaging the data from the processed digital signal into data packets; and

interspersing data packets with the voice packets.

11. A method for digital signal manipulation, comprising:

receiving an acoustic analog signal at a user system;

converting the analog signal to a digital signal;

canceling noise and echoes from the digital signal to form a processed digital signal;

detecting user speech in the processed digital signal by evaluating change in amplitude sign of the processed digital signal;

detecting vehicle information associated with the user speech; and

if user speech is detected in the processed digital signal,

packaging the user speech into speech packets to form a packaged voice signal;

selecting a transmission format compatible with the packaged voice signal; and

transmitting the packaged voice signal and vehicle information to a server.

12. The method of claim 11, wherein detecting user speech comprises evaluating rate of amplitude change in the processed digital signal.

13. The method of claim 11, further comprising:

matching the user speech of the voice signal with instructions stored in the server database; and

executing the instructions stored in the server database based on the user speech of the voice signal.

14. The method of claim 13, wherein matching the user speech at the server comprises statistical modeling and grammar analysis of the user speech.

15. The method of claim 11, wherein the user system is implemented in a vehicle.

16. The method of claim 11, wherein the packaged voice signal is transmitted to the server via wireless transmission.

17. The method of claim 11, comprising if user speech is not detected in the processed digital signal,

receiving non-acoustic data at the user system;

packaging the processed digital signal into data packets to form a packaged data signal;

selecting a transmission format compatible with the packaged data signal; and

transmitting the packaged data signal to a server.

18. The method of claim 17, wherein the packaged data signal is transmitted to the server using a maximum possible bandwidth.

19. The method of claim 11, wherein if user speech is detected in the processed digital signal, further comprising:

evaluating the processed digital signal to determine whether data exist that enhances speech detection and matching at the server; and

if data from the processed digital signal exists to be transmitted to the server to enhance speech detection and matching at the server,

packaging the data from the processed digital signal into data packets; and

interspersing data packets with the voice packets.

20. A system comprising:

a user system configured for receiving an acoustic analog signal and converting to a digital signal, where at the user system the system further comprises;

a processor having;

a first algorithm for canceling noise and echoes from the digital signal to form a processed digital signal;

a second algorithm for detecting speech in the processed digital signal by examining for the change in amplitude sign and the rate of amplitude change in the processed digital signal;

a third algorithm for packaging the processed digital signal with data or speech packets in accordance with the detected user speech to form a packaged voice signal;

a fourth algorithm for selecting a transmission format in accord with the packaged voice signal;

a fifth algorithm for determining vehicle information associated with the user speech; and

means for transmitting the digital signal and the vehicle information to a server, the server having a plurality of algorithms, wherein the plurality of algorithms match the speech content of the packaged voice signal with instructions stored in the server database to execute the instructions.

21. The system of claim 20, wherein the second algorithm further includes end-pointing the detected speech.

22. The system of claim 20, wherein at the server the method further comprises matching the speech content of the packaged voice signal with instructions stored in the server database and executing the instructions.

23. The system of claim 20, wherein the user system is implemented in a vehicle.

24. The system of claim 20, wherein transmitting is wireless.

25. The system of claim 20, wherein matching the speech content at the server includes statistical modeling and grammar to determine the best form to match the server database stored instructions.