Method and apparatus for selective distributed speech recognition

• US 7,197,331 B2
• Filed: 12/30/2002
• Issued: 03/27/2007
• Est. Priority Date: 12/30/2002
• Status: Active Grant

• Current Assignee: Google Technology Holdings LLC (Alphabet Inc.)
• Original Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Inventors: Balasuriya, Senaka, Anastasakos, Tasos, Van Wie, Michael
• Primary Examiner(s): Feild; Joseph
• Assistant Examiner(s): Nguyen; Huy D
• Application Number:
  US10/334,158
• Publication Number:
  US 20040192384A1
• Time in Patent Office: 1,548 Days
• Field of Search: 455/557, 455/563, 455/550.1, 455/413, 455/511, 455/67.7, 455/79, 455/116, 704/270.1, 704/231, 704/275
• US Class Current: 455/557
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: H04M 1/72451 according to schedules, e.g. using calendar applications
• CPC Class Codes: H04M 1/72457 according to geographic location
• CPC Class Codes: H04M 2250/74 with voice recognition means voice activated dialling H04M1/271; voice recognition algorithms G10L15/00

Abstract

A method and apparatus for selective distributed speech recognition includes an embedded speech recognition engine (104) and a dialog manager (102), such as a browser, coupled to the embedded speech recognition engine (104). The method and apparatus further includes the dialog manager (102) being operably couple able to at least one external speech recognition engine (106), such as a WLAN speech recognition engine (108) or a network speech recognition engine (110). The method and apparatus further includes preference information (114), environment information (112) and a speech input (116) all provided to the dialog manager (102). The dialog manager (102), in response to the preference information (114) and the environment information (112), provides the speech input (116) to the embedded speech recognition engine (104), the WLAN speech recognition engine (108) or the network speech recognition engine (110).

Claims

1. A wireless device comprising:

an embedded speech recognition engine;

a dialog manager operably coupled to the embedded speech recognition engine and operably coupleable to at least one external speech recognition engine;

preference information received by the dialog manager; and

environment information received by the dialog manager wherein the environment information includes information that describes a particular environment within which speech recognition can be performed, and wherein the dialog manager receives a speech input and the dialog manager, in response to the preference information and the environment information, provides the speech input to at least one of;

the embedded speech recognition engine and the at least one external speech recognition engine.

2. The wireless device of claim 1, wherein the environment information is provided from a wireless local area network.

3. The wireless device of claim 2, wherein the environment information is disposed within a wireless local area network profile and the environment information includes at least one of the following:

location information, time information, quality of service information, price information, and system availability information.

4. The wireless device of claim 1, wherein the at least one external speech recognition engine includes a wireless local area network speech recognition engine and a network speech recognition engine.

5. The wireless device of claim 4, wherein when the speech input is provided to the wireless local area network speech recognition engine through a wireless area network access point.

6. The wireless device of claim 1 further comprising:

a memory device operably coupled to the dialog manager, wherein memory device provides the preference information to the dialog manager, wherein the memory device is capable of receiving preference information from the dialog manager.

7. The wireless device of claim 1, wherein the preference information includes at least one of the following:

a pricing preference, a time preference, a quality of service preference, a language preference and a system availability preference.

8. A method for selective distributed speech recognition comprising:

receiving a speech input;

receiving preference information;

receiving environment information wherein the environment information includes information that describes a particular environment within which speech recognition can be performed; and

providing the speech input to at least one of the following;

a first speech recognition engine and at least one second speech recognition engine based on the preference information and the environment information.

9. The method of claim 8, wherein the first speech recognition engine is an embedded speech recognition engine and the at least one second speech recognition engine is at least one external speech recognition engine.

10. The method of claim 9, wherein the at least external speech recognition engine includes a wireless local area network speech recognition engine and a network speech recognition engine.

11. The method of claim 8, wherein the environment information is disposed within a wireless local area network profile and the environment information includes at least one of the following:

location information, time information, quality of service information, price information, and system availability information.

12. The method of claim 11, wherein the wireless local area network profile is received from a wireless local area network.

13. The method of claim 12, wherein the preference information is received from a memory device.

14. The method of claim 8, wherein the preference information includes at least one of the following:

a pricing preference, a time preference, a quality of service preference, a language preference and a system availability preference.

15. The method of claim 8 further comprising:

receiving at least one recognized term from at least one of the following;

the first speech recognition engine and the at least one second speech recognition engine;

providing the at least one recognized term to an output device; and

receiving a final confirmation of a correct recognized term of the at least one recognized term.

16. An apparatus for selective distributed speech recognition comprising:

a memory storing executable instructions; and

one or more processes that, in response to executing the executable instructions;

receive preference information;

receive environment information wherein the environment information includes information that describes a particular environment within which speech recognition can be performed; and

provide a speech input to at least one of the following;

an embedded speech recognition engine and at least one external speech recognition engine based on the received preference information and the received environment information.

17. The apparatus of claim 16, wherein the at least one external speech recognition engine includes a wireless local area network speech recognition engine and a network speech recognition engine.

18. The apparatus of claim 16, wherein the environment information is disposed within a wireless local area network profile and the environment information includes at least one of the following:

location information, time information, quality of service information, price information, and system availability information.

19. The apparatus of claim 16, wherein the preference information includes at least one of the following:

a pricing preference, a time preference, a quality of service preference, a language preference and a system availability preference.

20. An apparatus for selective distributed speech recognition comprising:

an embedded speech recognition engine;

a dialog manager operably coupled to the embedded speech recognition engine and operably couple able to at least one of the following;

a wireless area network speech recognition engine and a network speech recognition engine;

a memory device operably coupled to the dialog manager;

preference information received by the dialog manager from the memory device; and

environment information received by the dialog manager from a wireless area network profile transmitted by a wireless area network wherein the environment information includes information that describes a particular environment within which speech recognition can be performed, and wherein the dialog manager receives a speech input such that the dialog manager, in response to the preference information and the environment information, provides the speech input to at least one of;

the embedded speech recognition engine and the at least one external speech recognition engine.

21. The apparatus of claim 20, wherein the environment information includes at least one of the following:

location information, time information, quality of service information, price information, and system availability information.

22. The apparatus of claim 20, wherein the preference information includes at least one of the following:

a pricing preference, a time preference, a quality of service preference, a language preference and a system availability preference.

23. A method for selective distributed speech recognition comprising:

receiving a speech input;

receiving preference information from a memory device;

receiving environment information from a wireless area network profile wherein the environment information includes information that describes a particular environment within which speech recognition can be performed; and

providing the speech input to at least one of the following;

an embedded speech recognition engine, a wireless area network speech recognition engine and a network speech recognition engine, based on the preference information and the environment information.

24. The method of claim 23, wherein the environment information includes at least one of the following:

location information, time information, quality of service information, price information, and system availability information.

25. The method of claim 23, wherein the preference information includes at least one of the following:

a pricing preference, a time preference, a quality of service preference, a language preference and a system availability preference.

26. The method of claim 23 further comprising:

receiving at least one recognized term from at least one of the following;

the embedded speech recognition engine, the network speech recognition engine and the wireless local area network speech recognition engine;

providing the at least one recognized term to an output device; and

receiving a final confirmation of a correct recognized term of the at least one recognized term.