VOICE INTERFACE AND SEARCH FOR ELECTRONIC DEVICES INCLUDING BLUETOOTH HEADSETS AND REMOTE SYSTEMS

• US 20090204410A1
• Filed: 07/10/2008
• Published: 08/13/2009
• Est. Priority Date: 02/13/2008
• Status: Active Grant

• Current Assignee: Sensory Incorporated
• Original Assignee: Sensory Incorporated
• Inventors: Mozer, Todd F., Mozer, Forrest S.
• Granted Patent: US 8,195,467 B2
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: H04M 1/6066 including a wireless connection
• CPC Class Codes: H04M 3/42204 Arrangements at the exchange for service or number selection by voice at the terminal H04M1/27
• CPC Class Codes: H04M 3/4935 Connection initiated by DAS system

Abstract

Systems and methods for improving the interaction between a user and a small electronic device such as a Bluetooth headset are described. The use of a voice user interface in electronic devices may be used. In one embodiment, recognition processing limitations of some devices are overcome by employing speech synthesizers and recognizers in series where one electronic device responds to simple audio commands and sends audio requests to a remote device with more significant recognition analysis capability. Embodiments of the present invention may include systems and methods for utilizing speech recognizers and synthesizers in series to provide simple, reliable, and hands-free interfaces with users.

Claims

1. A wireless electronic device comprising:

a microphone for receiving a speech input;

a speech recognizer coupled to the microphone to receive the speech input;

a memory, the memory comprising a stored resource access number; and

a wireless transceiver for sending information from the electronic device to one or more other electronic devices,

wherein the speech recognizer is configured to recognize a first spoken command word, and wherein if the first command word is recognized in the speech input, then the speech recognizer generates a corresponding first command result, and

wherein if the first command result matches a predefined criteria, then the electronic device automatically accesses the resource access number from memory and sends the resource access number and an externally executed command through said transmitter to a second electronic device, and

wherein the externally executed command, when executed, uses the resource access number to establish a communication channel between said second electronic device and at least one remote device.

2. The device of claim 1 wherein the at least one remote device comprises a voice search engine.

3. The device of claim 2 wherein the resource access number accesses a root node of the voice search engine.

4. The device of claim 1 wherein the memory comprises a plurality of stored resource access numbers, wherein the speech recognizer is configured to recognize a plurality of spoken command words for accessing each stored resource access number, and wherein different resource access numbers access different nodes of a voice search engine search tree.

5. The device of claim 1 wherein the wireless transceiver is a Bluetooth transceiver.

6. The device of claim 1 wherein the wireless device is a headset and the second electronic device is a cellular phone.

7. The device of claim 1 wherein the communication channel comprises a telephone network.

8. The device of claim 1 wherein the communication channel comprises a cellular network.

9. The device of claim 1 wherein the communication channel comprises an Internet.

10. The device of claim 1 wherein the resource access number is pre-stored in non-volatile memory.

11. The device of claim 1 wherein the resource access number is a telephone number.

12. The device of claim 1 wherein the resource access number is a URL.

13. A method comprising:

receiving input speech from a user in an electronic device;

recognizing the input speech on the electronic device, and outputting a command if the input speech is recognized as an utterance in a word set of a recognizer;

accessing a resource access number stored in a memory of the electronic device if the command matches a predefined criteria; and

sending the resource access number and an externally executed command to a second electronic device,

wherein the externally executed command, when executed, instructs the second electronic device to use the resource access number to establish a communication channel between said second electronic device and at least one remote device.

14. The method of claim 13 wherein the at least one remote device comprises a voice search engine.

15. The method of claim 14 wherein the resource access number accesses a root node of the voice search engine.

16. The method of claim 13 wherein the memory comprises a plurality of stored resource access numbers, and wherein the word set of the recognizer is configured to recognize a plurality of utterances corresponding to the stored resource access numbers, and wherein a first resource access number is accessed if a corresponding first utterance is recognized and a second resource access number is accessed if a corresponding second utterance is recognized, and wherein different resource access numbers access different nodes of a voice search engine search tree.

17. The method of claim 13 wherein the resource access number and the externally executed command are sent to the second electronic device across a wireless network.

18. The method of claim 13 wherein the electronic device is a headset and the second electronic device comprises a cellular phone.

19. The method of claim 13 wherein the communication channel comprises a telephone network.

20. The method of claim 13 wherein the communication channel comprises a cellular phone network.

21. The method of claim 13 wherein the communication channel comprises an Internet.

22. The method of claim 13 wherein the resource access number is a telephone number.

23. The method of claim 13 wherein the resource access number is a URL.

24. A wireless electronic device comprising:

a speech recognizer coupled to receive the speech input;

a memory, the memory comprising one or more stored resource access numbers;

a voice user interface for interacting with a user using speech recognition or speech synthesis; and

a wireless transceiver for communicating with at least one remote device,

wherein the remote device comprises a voice search engine,

wherein the electronic device is configured to allow a user to interact with the electronic device primarily through the voice user interface, and

wherein the speech recognizer is configured to recognize a first spoken command word, and wherein if the first command word is recognized in the speech input, then the speech recognizer generates a corresponding first command result, and

wherein if the first command result matches a predefined criteria, then the electronic device automatically accesses the resource access number from memory and establishes a communication channel between said wireless electronic device and the at least one remote device, and

wherein, after establishing the communication channel, input speech from a user is transmitted to said voice search engine through said wireless electronic device.

25. The method of claim 24 wherein the resource access number is a URL.

26. The method of claim 24 wherein the resource access number is a telephone number.

27. The method of claim 24 wherein the memory comprises a plurality of stored resource access numbers, and wherein the speech recognizer is configured to recognize a plurality of spoken command words to recognize a plurality of utterances corresponding to the stored resource access numbers, and wherein a first resource access number is accessed if a corresponding first utterance is recognized and a second resource access number is accessed if a corresponding second utterance is recognized, and wherein different resource access numbers access different nodes of a voice search engine search tree.

28. The method of claim 24 wherein the communication channel comprises a telephone network.

29. The method of claim 24 wherein the communication channel comprises a cellular phone network.

30. The method of claim 24 wherein the communication channel comprises an Internet.

31. The method of claim 24 wherein the communication channel comprises a wireless network.