METHOD AND APPARATUS FOR MACHINE TO MACHINE COMMUNICATION USING SPEECH

• US 20030093281A1
• Filed: 05/21/1999
• Published: 05/15/2003
• Est. Priority Date: 05/21/1999
• Status: Abandoned Application

• Current Assignee: Winbond Electronics Corporation
• Original Assignee: Winbond Electronics Corporation
• Inventors: MACMILLAN, DAVID, BAREL, AVRAHAM, BROWN, AMOS, PYO, PHILLIP, GADDY, LAWRENCE, GEILHUFE, MICHAEL, BOOTSMA, KARIN
• Application Number:
  US09/316,666
• Publication Number:
  US 20030093281A1
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

Voice controlled devices with speech recognition have user assignable appliance names and default appliance names to address and control the voice controlled devices. Methods of controling voice controlled devices include addressing a voice controlled device by name and providing a command.

Claims

1. A method for machine to machine communication using speech, the method comprising:

providing a first device having a speech generation capability;

providing a second device having a speech recognition capability;

communicating speech from the first device to the second device; and

causing the second device to recognize the speech.

2. The method of claim 1 for machine to machine communication using speech, wherein,

the speech is communicated using audible speech.

3. The method of claim 1 for machine to machine communication using speech, wherein,

the speech is communicated using non-audible speech.

4. A method for machine to machine communication using speech, the method comprising:

providing a first device having a speech generation capability,

providing a second device having a speech recognition capability and at least one stored phrase,

communicating speech from the first device to the second device, the speech including at least a phrase, and

causing the second device to determine if it recognizes the communicated phrase as matching at least one of the at least one stored phrase.

5. The method of claim 4 for machine to machine communication using speech, wherein,

the at least one stored phrase is stored in a speaker independent representation.

6. The method of claim 4 for machine to machine communication using speech, wherein,

the at least one stored phrase is stored in a phonetic representation.

7. The method of claim 4 for machine to machine communication using speech, wherein,

the speech recognition capability is speaker independent.

8. The method claim 7 for machine to machine communication using speech of, wherein,

the speech is communicated using audible speech.

9. The method claim 7 for machine to machine communication using speech of, wherein,

the speech is communicated using non-audible speech.

10. A method for machine to machine communication using speech, the method comprising:

providing a first device having a speech generation capability,

providing a second device having a speech recognition capability and at least one stored appliance name and at least one stored command,

communicating speech from the first device to the second device, the speech including at least a communicated appliance name and at least a communicated command, and

causing the second device to determine if it recognizes the communicated appliance name as matching at least one of the at least one stored appliance name.

11. The method of claim 10 for machine to machine communication using speech, the method further comprising,

causing the second device to additionally determine if the communicated command matches at least one of the at least one stored command.

12. The method of claim 11 for machine to machine communication using speech, wherein,

the at least one stored appliance name and the at least one stored command are stored in a speaker independent representation.

13. The method of claim 11 for machine to machine communication using speech, wherein,

the at least one stored appliance name and the at least one stored command are stored in a phonetic representation.

14. The method of claim 11 for machine to machine communication using speech, wherein,

the speech recognition capability is speaker independent.

15. The method of claim 14 for machine to machine communication using speech, wherein,

the speech is communicated using audible speech.

16. The method of claim 14 for machine to machine communication using speech, wherein,

the speech is communicated using non-audible speech.

17. A method for machine to machine communication using speech, the method comprising:

providing a first device having a first speech generation capability and a first speech recognition capability,

providing a second device having a first speech generation capability and a second speech recognition capability,

communicating first speech from the first device to the second device,

causing the second device to recognize the first speech,

communicating second speech from the second device to the first device, and

causing the first device to recognize the second speech.

18. The method of claim 17 for machine to machine communication using speech, wherein,

the speech is communicated using audible speech.

19. The method of claim 17 for machine to machine communication using speech, wherein,

the speech is communicated using non-audible speech.

20. A method for machine to machine communication using speech, the method comprising:

providing a first device having a first speech generation capability and a first speech recognition capability and a first at least one stored phrase,

providing a second device having a second speech generation capability and a second speech recognition capability and a second at least one stored phrase,

communicating first speech that includes at least a first phrase from the first device to the second device,

causing the second device to determine if it recognizes the communicated first phrase as matching at least one of the second at least one stored phrase,

communicating second speech that includes at least a second phrase from the second device to the first device, and

causing the first device to determine if it recognizes the communicated second phrase as matching at least one of the first at least one stored phrase.

21. The method for machine to machine communication using speech of claim 20, wherein,

at least one of the first or second at least one stored phrase is stored in a speaker independent representation.

22. The method for machine to machine communication using speech of claim 20, wherein,

at least one of the first or second at least one stored phrase is stored in a phonetic representation.

23. The method for machine to machine communication using speech of claim 20, wherein,

at least one of the first or second speech recognition capability is speaker independent.

24. The method for machine to machine communication using speech of claim 20, wherein,

the first or second speech is communicated using audible speech.

25. The method for machine to machine communication using speech of claim 20, wherein,

the first or second speech is communicated using non-audible speech.