Speech-responsive voice messaging system and method

• US 6,522,726 B1
• Filed: 02/14/2000
• Issued: 02/18/2003
• Est. Priority Date: 03/24/1997
• Status: Expired due to Term

• Current Assignee: Avaya Incorporated
• Original Assignee: Avaya Technology Corporation Miami Lakes FLA US
• Inventors: Grajski, Kamil, Rub, Leonardo, Albright, Susannah, Hunt, Peter
• Primary Examiner(s): Weaver, Scott L.
• Application Number:
  US09/503,655
• Time in Patent Office: 1,100 Days
• Field of Search: 379/67.1, 379/88.01, 379/88.02, 379/88.03, 379/88.04, 379/88.08, 379/88.22, 379/88.23, 379/88.24, 704/200, 704/231, 704/246, 704/291, 704/270
• US Class Current: 379/88.04
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A system and method for speech-responsive voice messaging, in which a Speech-Responsive Voice Messaging System (SRVMS) preferably provides a hierarchically-simple speech user interface (UI) that enables subscribers to use speech to specify commands such as mailboxes, passwords, and digits. The SRVMS generates and evaluates candidate results. The SRVMS invokes a speech UI navigation operation or a voice messaging operation according to the outcome of the evaluation of the candidate results. In the preferred embodiment, the SRVMS determines whether the candidate results are good, questionable, or bad; and whether two or more candidate results are ambiguous due to a likelihood that each such result could be a valid command. If the candidate results are questionable or ambiguous, an ambiguity resolution UI prompts the subscriber to confirm whether the best candidate result is what the subscriber intended. In response to repeated speech recognition failures, the SRVMS transfers the subscriber to a Dual Tone Multi Frequency (DTMF) UI. Transfer to the DTMF UI is also performed in response to detection of predetermined DTMF signals issued by the subscriber while the speech UI is in context. The SRVMS provides a logging unit and a reporting unit which operate in parallel with the speech UI, in a manner that is transparent to subscribers. The logging unit directs the selective logging of subscriber utterances, and the reporting unit selectively generates and maintains system performance statistics on multiple detail levels.

Claims

1. A method of recognizing instructions from a user, the method comprising the steps of:

a. simultaneously providing a speech user interface configured to accept an audible utterance from the user and a dual tone multi frequency user interface configured to accept a dual tone multi frequency signal input from the user, wherein the speech user interface includes a command structure-different than a command structure of the dual tone multi frequency user interface;

b. receiving a response generated by the user, wherein the response is one selected from a group consisting of an appropriate audible utterance and an appropriate dual tone multi frequency signal input; and

c. automatically identifying the appropriate audible utterance as speech originating from the user and the appropriate dual tone multi frequency signal input as at least one touchtone key actuated by the user.

2. The method according to claim 1 further comprising the step of providing a template library having a plurality of speech templates, each corresponding to a command available for the user, wherein the template library facilitates the step of automatically identifying.

3. The method according to claim 2 wherein the template library includes a plurality of speaker dependent speech templates and a plurality o independent speech templates.

4. The method according to claim 2 wherein the template library includes a plurality of speaker independent speech templates.

5. The method according to claim 2 wherein the template library includes a plurality of speaker dependent speech templates.

6. A method of recognizing instructions from a user interacting with a voice messaging system having a plurality of voice messaging functions, the method comprising the steps of:

a. providing a speech user interface for accepting an appropriate utterance from the user;

b. performing a matching operation on the appropriate utterance to obtain a candidate result, wherein the candidate result indicates existence of a potential match between one of a plurality of commands and the appropriate utterance, each command corresponding to one of the plurality of voice messaging functions;

c. evaluating the candidate result to determine whether an unsuccessful match condition exits;

d. repeating steps (a) through (c) upon the occurrence of the unsuccessful match condition and before the occurrence of a predetermined number of consecutive unsuccessful match conditions; and

e. automatically transferring the user to a dual tone multi frequency user interface for accepting a dual tone multi frequency signal input from the user upon the occurrence of the predetermined number of consecutive unsuccessful match conditions.

7. The method according to claim 6 wherein the step of providing a speech user interface includes the steps of:

a. generating an appropriate voice prompt to the user; and

b. detecting the appropriate utterance from the user.

8. The method according to claim 7 wherein the step of detecting the appropriate utterance includes the steps of:

a. detecting an appropriate dual tone multi frequency signal input from the user;

b. automatically transferring the user to the dual tone multi frequency user interface if the appropriate dual tone multi frequency signal input is detected; and

c. processing the appropriate dual tone multi frequency signal input from the user if the appropriate dual tone multi frequency signal input is detected.

9. The method according to claim 8 further including the step of automatically transferring the user to the speech user interface once the step of processing the appropriate dual tone multi frequency signal input from the user is complete.

10. The method according to claim 6 further comprising the step of providing a template library having a plurality of speaker independent speech templates, each corresponding to one of the plurality of commands, wherein the template library facilitates the step of performing a matching operation.

11. The method according to claim 10 wherein the template library includes a plurality of speaker dependent speech templates, each corresponding to one of the plurality of commands.

12. The method according to claim 6 further comprising the steps of:

a. incrementing an unsuccessful match count index for each occurrence of the unsuccessful match condition; and

b. determining whether the unsuccessful match count index has exceeded a predetermined limit.

13. The method according to claim 12 further comprising the steps of:

a. setting a repeat status indicator upon the occurrence of the unsuccessful match condition and while the unsuccessful match count index has not exceeded the predetermined limit, wherein the repeat status indicator determines whether an additional utterance from the user is necessary because of the occurrence of the unsuccessful match condition; and

b. setting a predetermined limit exceeded status indicator upon the occurrence of the unsuccessful match condition and if the unsuccessful match count index has exceeded the predetermined limit, wherein the predetermined limit exceeded status indicator determines whether to automatically transfer the user form the speech user interface to the dual tone multi frequency user interface because of the occurrence of the unsuccessful match condition.

14. A voice messaging system comprising a user interface following a user to selectively activate each one of a plurality of voice messaging functions, wherein the user interface comprises a speech user interface for accepting an utterance from the user and a dual tone multi frequency user interface for accepting a dual tone multi frequency signal input from the user when the user selects any one of the plurality of voice messaging functions, further wherein the speech user interface includes a command structure different than a command structure of the dual zone multi frequency user interface.

15. The voice messaging system according to claim 14 further comprising:

a. means coupled to the user interface for performing a matching operation on the utterance from the user to obtain a candidate result, wherein the candidate result indicates existence of a potential match between one of a plurality of commands and the utterance, each command corresponding to one of the plurality of voice messaging functions;

b. means coupled to the user interface for evaluating the candidate result to determine whether an unsuccessful match condition exists, wherein the unsuccessful match condition directs the user interface to prompt the user to select another one of the plurality of voice messaging functions;

c. means couple to the user interface for transferring the user between the speech user interface and the dual tone multi frequency user interface, wherein the means for transferring automatically transfers the user from the speech user interface to the dual tone multi frequency user interface upon the occurrence of a predetermined number of consecutive unsuccessful match conditions.

16. The voice messaging system according to claim 15 wherein the speech user interface includes:

a. means for generating a voice prompt to the user; and

b. means for detecting the utterance from the user.

17. The voice messaging system according to claim 16 further comprising:

a. means for detecting the dual tone multi frequency signal input from the user; and

b. means for processing the dual tone multi frequency signal input from the user.

18. The voice messaging system according to claim 17 wherein the means for transferring automatically transfers the user from the speech user interface to the dual tone multi frequency user interface if the means for detecting the dual tone multi frequency signal input detects the dual tone multi frequency signal input from the user in response to the voice prompt to the user by the means for generating.

19. The voice messaging system according to claim 18 wherein the means for transferring transfers the user from the dual tone multi frequency user interface to the speech user interface upon the means for processing completing the processing of the dual tone multi frequency input from the user.

20. The voice messaging system according to claim 15 further comprising a template library having a plurality of speaker independent speech templates, each corresponding to one of the plurality of commands, wherein the template library facilitates matching one of the plurality of commands to the utterance.

21. The voice messaging system according to claim 20 wherein the template library includes a plurality of speaker dependent speech templates, each corresponding to one of the plurality of commands.

22. The voice messaging system according to claim 15 further comprising:

a. an unsuccessful match count index, wherein the unsuccessful match count index is incremented upon each occurrence of the unsuccessful match condition; and

b. means for determining whether the unsuccessful match count index has exceeded a predetermined limit.

23. The voice messaging system according to claim 22 further comprising:

a. a repeat status indicator, wherein the repeat status indicator is set upon the occurrence of the unsuccessful match condition and while the unsuccessful match count index has not exceeded the predetermined limit, further wherein the repeat status indicator determines whether an additional utterance from the user is necessary because of the occurrence of the unsuccessful match condition; and

b. a predetermined limit exceeded status indicator, wherein the predetermined limit exceeded status indicator is set upon the occurrence of the unsuccessful match condition and if the unsuccessful match count index has exceeded the predetermined limit, further wherein the predetermined limit exceeded status indicator determines whether to transfer the user from the speech user interface to the dual tone multi frequency user interface because of the occurrence of the unsuccessful match condition.