Method for entering digit sequences by voice command

• US 4,870,686 A
• Filed: 10/19/1987
• Issued: 09/26/1989
• Est. Priority Date: 10/19/1987
• 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): Shoop, Jr., William M.
• Assistant Examiner(s): Hoff, Marc S.
• Application Number:
  US07/110,144
• Time in Patent Office: 708 Days
• Field of Search: 381/36, 381/41, 381/43, 364/513.5, 379/354-356
• US Class Current: 704/234
• 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

Abstract

A user-interactive speech recognition control system is disclosed for recognizing a complete sequence of keywords (e.g., a telephone number such as 123-4567) via entering, verifying, and editing variable-length utterance strings (e.g., 1-2-3; 4-5; 6-7) separated by the user-defined placement of pauses. The device controller (120) utilizes timers (124) to monitor the pause time between partial-sequence digit strings recognized by the speech recognizer (110). When a string of digits is followed by a predetermined pause time interval, the recognized digits will be replied via the speech synthesizer (130). An additional string of digits can then be entered, and only the subsequent string will be replied after the next pause. Furthermore, the user has the flexibility to correct only the last digit string entered, or the entire sequence. Hence, if there is an error in only one digit, the erroneous digit string can be corrected without having to re-enter the entire digit sequence. The invention is well-suited to be used in a hands-free voice command dialing system for a mobile radiotelephone, wherein vehicular background noise may affect recognition accuracy.

Claims

1. A user-interactive method of controlling an electronic device comprising:

recognizing keywords contained in at least two variable-length speech utterance string separated by a pause time interval,

providing a pause signal after an utterance string has ceased for a predetermined pause time;

providing an indication to the user, in response to said pause signal, of particular keywords, recognized which correspond to an utterance string occurring before said pause signal; and

correcting particular keywords in response to said pause signal and in response to the recognition of a predetermined error command keyword contained in an utterance string occurring after said pause signal.

2. The method according to claim 1, wherein said recognizing step includes the step of storing particular recognized keywords into memory.

3. The method according to claim 2, wherein said indication providing step includes the step of reading said stored keywords from memory

4. The method according to claim 1, wherein said correcting step includes the step of providing an indication to the user of the recognition of said predetermined error command keyword.

5. The method according to claim 2, wherein said correcting step includes the step of clearing stored keywords from memory which correspond to only the last utterance string occurring before said pause signal, in response to the recognition of said predetermined error command keyword.

6. The method according to claim 2, wherein said correcting step further includes the steps of:

recognizing two identical error command keywords contained in consecutive utterance strings; and

clearing all keywords stored in memory in response to such recognition.

7. The method according to claim 2, further comprising the steps of:

recognizing a predetermined stop command keyword contained in an utterance string; and

outputting all keywords stored in memory in response to such recognition.

8. The method according to claim 1, wherein said indication providing step further includes the step of providing an indication to the user of the occurrence of a speech utterance without any corresponding keyword recognition.

9. The method according to claim 1, wherein said predetermined pause time is not greater than five seconds.

10. A user-interactive speech recognition control apparatus comprising:

means for recognizing keywords contained in at least two variable-length speech utterance strings separated by a pause time interval;

means for providing a pause signal after an utterance string has ceased for a predetermined pause time;

means, responsive to said pause signal, for providing an indication to the user of particular keywords recognized which correspond to the last utterance string occurring before said pause signal; and

means, further responsive to said pause signal, for correcting said particular keywords in response to the recognition of a predetermined error command keyword contained in the next utterance string occurring after said pause signal

11. The apparatus according to claim 10, wherein said control apparatus is an automatic dialer for a telecommunications device.

12. The apparatus according to claim 11, wherein said telecommunications device is a radiotelephone.

13. The apparatus according to claim 11, wherein said telecommunications device includes a speakerphone.

14. The apparatus according to claim 10, wherein said recognizing means implements continuous-word speech recognition.

15. The apparatus according to claim 10, wherein said recognizing means includes means for storing particular recognized keywords into memory.

16. The apparatus according to claim 15, wherein said indication providing means includes means for reading said stored keywords from memory.

17. The apparatus according to claim 10, wherein said indication providing means includes a speech synthesizer.

18. The apparatus according to claim 10, wherein said indication providing means includes a visual display.

19. The apparatus according to claim 10, wherein said predetermined pause time is not greater than five seconds.

20. The apparatus according to claim 10, wherein said correcting means includes means for providing an indication to the user of the recognition of said predetermined error command keyword.

21. The apparatus according to claim 15, wherein said correcting means further includes means for clearing stored keywords from memory which correspond to only the last utterance string occurring before said pause signal, in response to the recognition of said predetermined error command keyword.

22. The apparatus according to claim 15, wherein said correcting means further includes:

means for recognizing two identical error command keywords contained in consecutive utterance strings; and

means for clearing all keywords stored in memory in response to such recognition.

23. The apparatus according to claim 10, wherein said indication providing means further includes means for providing an indication to the user of the occurrence of a speech utterance without any corresponding keyword recognition.

24. The apparatus according to claim 15, further comprising:

means for recognizing a predetermined stop command keyword contained in an utterance string; and

means for outputting all keywords stored in memory in response to such recognition.

25. A method of entering a complete sequence of speech utterances comprised of a plurality of variable-length utterance strings into a speech recognition controller which provides a data output corresponding to keywords contained in said complete sequence, each utterance string followed by a pause time interval, and each utterance string containing at least one keyword, said method comprising the steps of:

(a) recognizing a first utterance string as corresponding to a first keyword set;

(b) storing said first recognized keyword set into read/write memory;

(c) providing a pause signal after said first utterance string has ceased for a predetermined pause time interval;

(d) retrieving said first stored keyword set from memory in response to said pause signal;

(e) providing an indication to the user of at least said first retrieved keyword set;

(f) recognizing a second utterance string as corresponding to a predetermined error command keyword; and

(g) correcting said first stored keyword set in response to the recognition of said predetermined error command keyword.

26. The method according to claim 25, wherein said recognizing steps implement continuous-word speech recognition.

27. The method according to claim 25, wherein said indication providing step includes the step of synthesizing speech corresponding to only said first keyword set.

28. The method according to claim 25, wherein said indication providing step further includes the step of visually displaying all stored keywords.

29. The method according to claim 25, wherein said predetermined pause time is not greater than five seconds.

30. The method according to claim 25, wherein said correcting step further includes the step of providing an indication to the user of the recognition of said predetermined error command keyword.

31. The method according to claim 25, wherein said correcting step further includes the step of clearing only said first stored keyword set from memory in response to the recognition of said predetermined error command keyword.

32. The method according to claim 25, wherein said correcting step further includes the steps of:

recognizing two identical error command keywords contained in consecutive utterance strings; and

clearing all keywords stored in memory in response to such recognition.

33. The method according to claim 25, further comprising the steps of:

recognizing a predetermined stop command keyword contained in an utterance string; and

outputting all keywords stored in memory in response to such recognition.

34. The method according to claim 25, wherein said indication providing step further includes the step of providing an indication to the user of the occurrence of a speech utterance without any corresponding keyword recognition.