Method for terminating a telephone call by voice command

• US 4,945,570 A
• Filed: 08/25/1989
• Issued: 07/31/1990
• Est. Priority Date: 10/02/1987
• Status: Expired due to Term

• Current Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Original Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Inventors: Lindsley, Brett L., Gerson, Ira A.
• Primary Examiner(s): Stephan, Steven L.
• Assistant Examiner(s): Jones, Judson H.
• Application Number:
  US07/399,341
• Time in Patent Office: 340 Days
• Field of Search: 455/79, 379/58, 379/61, 379/389, 381/43, 381/46, 381/56, 381/110, 340/825.32
• US Class Current: 455/563
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: H04M 1/271 controlled by voice recognition
• CPC Class Codes: H04M 9/08 Two-way loud-speaking telephone systems with means for conditioning the signal, e.g. for suppressing echoes for one or both directions of traffic

Abstract

A reliable method for terminating a telephone call is disclosed using a specific sequence of steps performed by the hands-free control system. The invention requires that the call terminating command sequence be recognized as: (1) two separate speech utterances (e.g., TERMINATE and CONVERSATION); (2) in proper sequence (e.g., TERMINATE first, then CONVERSATION); (3) with a maximum pause time interval between the end of the first utterance and the start of the second utterance (e.g., 300 milliseconds); and (4) which meet predefined speech recognition matching criteria. Moreover, the present invention provides the user with a procedure to continue the telephone call in progress should the speech recognizer false, or if the user did not intend to speak the proper command. As a result, present invention enables a user to disconnect a telephone call by voice command with a high degree of reliability, even under high ambient noise conditions.

Claims

1. A speech communications device having a voice command system for controlling a voice communication path established by said speech communications device, said voice communication path being controlled by a command signal provided by said control system in response to user-spoken command words, said control system comprising:

speech recognition means for recognizing sequential first and second user-spoken utterances at least during the time said voice communication path is established, said speech recognition means including;

first means for recognizing, during the time said voice communication path is established, said first user-spoken utterance as one corresponding to a first predetermined command word, and for producing a first detect signal in response to such recognition,

second means for recognizing said second user-spoken utterance as one corresponding to a second predetermined command word, for producing a second detect signal if said second predetermined command word is recognized, and for cancelling said recognition of said first predetermined command word if said second predetermined command word is not recognized; and

decision means for providing said command signal in response to said second detect signal occurring within a predetermined recognition time interval after said first detect signal.

2. The speech communications device according to claim 1, further comprising:

third means for recognizing a third user-spoken utterance as one corresponding to third predetermined command word, and for producing a third detect signal in response to such recognition; and

correction means for preventing said decision means from providing said command signal if said third detect signal occurs within a predetermined verification time interval after said second detect signal.

3. The speech communications device according to claim 1, wherein said predetermined recognition time interval is less than 5 seconds.

4. The speech communications device according to claim 2, wherein said predetermined verification time interval is less than 10 seconds.

23. The speech communication device according to claim 1, wherein said first and second predetermined command words each have separate and distinct speech recognition templates.

24. The speech communication device according to claim 1, wherein said speech recognition means is only responsive to said second predetermined command word spoken during said predetermined recognition time interval.

25. The speech communication device according to claim 1, wherein said command signal functions to interrupt said voice communication path.

5. A speech communications device having a hands-free user-interaction voice command control system including means for switching said communications device from an off-hook mode, wherein a communications path is established, to on-hook mode, wherein said communications path is terminated, in response to an on-hook signal, said control system comprising:

first means for recognizing, in said off-hook mode, a first user-spoken utterance as one corresponding to a first predetermined terminate command word, and for producing a first detect signal in response to such recognition;

timer means for measuring a pause time interval between the end of said first user-spoken utterance and the start of a sequential second user-spoken utterance, and for providing a timer signal only if said measured pause time interval is less than a predetermined maximum pause time interval;

second means for recognizing said second user-spoken utterance as one corresponding to a second predetermined terminate command word, for producing a second detect signal if said second predetermined terminate command word is recognized, and for cancelling said first detect signal if said second predetermined terminate command word is not recognized; and

decision means for providing a disconnect signal only in response to said timer signal and the sequential occurrence of said first and second detect signals, such that the recognition of said second terminate command word does not cause termination of said communications path if said measured pause time interval exceeds said predetermined maximum pause time interval.

6. The speech communications device according to claim 5, further comprising:

means for providing an indication to a user in response to said disconnect signal;

third means for recognizing a user-spoken utterance as one corresponding to a predetermined error command word, and for producing an error signal in response to such recognition; and

correction means for providing said on-hook signal in response to said disconnect signal only if said error signal does not occur within a predetermined reconnect time interval after the occurrence of said disconnect signal, such that the recognition of said error command word within said predetermined reconnect time interval prevents the recognition of said terminate command words from causing termination of said communications path.

7. The speech communications device according to claim 5, wherein said speech communications device is a mobile radiotelephone.

8. The speech communications device according to claim 5, wherein said speech communications device includes a speakerphone.

9. The speech communication device according to claim 6, wherein said first, second, and third recognizing means implement connected-word speech recognition.

10. The speech communications device according to claim 5, wherein said first and second predetermined terminate command words each have at least two syllables.

11. The speech communications device according to claim 5, wherein said predetermined maximum pause time interval is less than 1 second.

12. The speech communications device according to claim 6, wherein said indication providing means is a speech synthesizer.

13. The speech communications device according to claim 6, wherein said predetermined reconnect time interval is less than 10 seconds.

26. The speech communication device according to claim 5, wherein said first and second predetermined terminate command words each have separate and distinct speech recognition templates.

27. The speech communication device according to claim 5, wherein said first and second recognizing means recognize user-spoken utterances at least when said communications path is established.

28. The speech communication device according to claim 5, wherein said disconnect signal is provided only when said first and second predetermined terminate command words are spoken during the time said communication path is established.

29. The speech communication device according to claim 5, further comprising means for providing said on-hook signal in response to said disconnect signal.

14. A method of controlling a speech communications device having speech recognition and device operational control capabilities for controlling a voice communication path established between said speech communications device and another device, said method comprising the steps of:

establishing said voice communication path;

recognizing, at least during the time said voice communication path is established, a first user-spoken utterance as one corresponding to a first predetermined command word, and producing a first detect signal in response to such recognition;

measuring a pause time interval between the end of said first user-spoken utterance and the start of a sequential second user-spoken utterance, and providing a timer signal only if said measured pause time interval is less than a predetermined maximum pause time interval;

recognizing said sequential second user-spoken utterance as one corresponding to a second predetermined command word, producing a second detect signal if said second predetermined command word is recognized, and returning to said recognizing a first user-spoken utterance step if said second predetermined command word is not recognized; and

providing a first device control signal only in response to said timer signal and the sequential occurrence of said first and second detect signals.

15. The method according to claim 14, further comprising the steps of:

providing an indication to a user in response to said first device control signal;

recognizing a third user-spoken utterance as one corresponding to a third predetermined command word, and producing an error signal in response to such recognition; and

producing a second device control signal in response to said first device control signal only if said error signal does not occur within a predetermined reconnect time interval after the occurrence of said first device control signal.

16. The method according to claim 14, wherein said speech communications device is a mobile radiotelephone.

17. The method according to claim 14, wherein said speech communications device includes a speakerphone.

18. The method according to claim 14, wherein all recognizing steps are performed using connected-word speech recognition.

19. The method according to claim 14, wherein said first and second predetermined command words each have at least two syllables.

20. The method according to claim 14, wherein said predetermined maximum pause time interval is less than 1 second.

21. The method according to claim 15, wherein said indication providing step is performed using speech synthesis.

22. The method according to claim 15, wherein said predetermined reconnect time interval is less than 10 seconds.

30. The method according to claim 14, wherein said first and second predetermined command words each have separate and distinct speech recognition templates.

31. The method according to claim 14, wherein said first device control signal is provided only when said first and second predetermined command words are spoken during the time said voice communication path is established.

32. The method according to claim 14, further comprising the step of interrupting said voice communication path in response to said first device control signal.

33. The method according to claim 15, wherein said second device control signal functions to interrupt said voice communication path.

34. A voice command control system for controlling a speech communications device having a voice communication path established for the user, said voice communication path being controlled by a command signal provided by said control system in response to user-spoken command words, said control system comprising:

first means for recognizing, during the time said voice communication path is established, a first user-spoken utterance as one corresponding to a first predetermined command word, and for producing a first detect signal in response to such recognition;

second means to recognizing a sequential second user-spoken utterance as one corresponding to a second predetermined command word, for producing a second detect signal if said second predetermined command word is recognized, and for cancelling the effect of said first predetermined command word recognition if said second predetermined command word is not recognized;

decision means for providing said command signal in response to the occurrence of both said first and second detect signals;

third means for recognizing a user-spoken utterance as one corresponding to a third predetermined command word, and for producing a third detect signal in response to such recognition; and

correction means for preventing said decision means from providing said command signal if said third detect signal occurs within a predetermined verification time interval after said second detect signal.

35. The voice command control system according to claim 34, wherein said first and second predetermined command words each have separate and distinct speech recognition templates.

36. The voice command control system according to claim 37, wherein said command signal is provided only when said second predetermined command word is spoken during said predetermined recognition time interval.

37. The voice command control system according to claim 34, wherein said decision means provides said command signal only in response to said second detect signal occurring within a predetermined recognition time interval after said first detect signal.

38. The voice command control system according to claim 37, wherein said command signal is provided only when said first and second predetermined command words are spoken during the time said voice communication path is established.

39. The voice command control system according to claim 34, wherein said command signal functions to interrupt said voice communication path.

40. A method of controlling an electronic device having speech recognition and device operational control capabilities for terminating a voice communication path established between said electronic device and another device, said method comprising the steps of:

recognizing, at least during the time said voice communication path is established, a first user-spoken utterance as one corresponding to a first predetermined command word, and producing a first detect signal in response to such recognition;

recognizing a subsequently-spoken utterance as one corresponding to a second predetermined command word, producing a second detect signal if said second predetermined command word is recognized, and cancelling said recognition of said first user-spoken utterance if said second predetermined command word is not recognized;

providing a first device control signal in response to the sequential occurrence of said first and second detect signals;

providing an indication to a user in response to said first device control signal;

recognizing a user-spoken utterance as one corresponding to a third predetermined command word, and producing an error signal in response to such recognition; and

terminating said voice communication path in response to said first device control signal only if said error signal does not occur within a predetermined reconnect time interval after the occurrence of said first device control signal.

41. The method according to claim 40, wherein said first and second predetermined command words are each recognized using separate and distinct speech recognition templates.

42. The method according to claim 40, further comprising the step of measuring a pause time interval between the end of said first user-spoken utterance and the start of said subsequently-spoken utterance, and providing said first device control signal only if said measured pause time interval does not exceed a predetermined maximum pause time interval.

43. The method according to claim 42, wherein only said second predetermined command word can be recognized during said maximum pause time interval.