Speech-responsive voice messaging system and method

• US 6,377,662 B1
• Filed: 02/14/2000
• Issued: 04/23/2002
• 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: Hunt, Peter, Grajski, Kamil, Rub, Leonardo, Albright, Susannah
• Primary Examiner(s): WEAVER, SCOTT LOUIS
• Application Number:
  US09/503,409
• Time in Patent Office: 799 Days
• Field of Search: 379/88.01, 379/88.02, 379/88.03, 379/88.04, 704/200, 704/201, 704/231, 704/251, 704/270, 704/275
• US Class Current: 379/88.01
• 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 analyzing performance of a speech recognition system, the method comprising the steps of:

a. selecting a speech parameter block, wherein the speech parameter block includes a data structure having a plurality of data fields, wherein the plurality of data fields includes a first data field for storing a plurality of logging parameters that control whether one or more speech communications between the speech recognition system and a user should be logged;

b. transparently monitoring the one or more speech communications between the speech recognition system and the user via the plurality of logging parameters; and

c. logging selective ones of the one or more speech communications as directed by the logging parameters, thereby forming a recorded speech communication to correspond with each of the one or more speech communications that is logged.

2. The method according to claim 1 wherein the plurality of logging parameters include:

a. a plurality of logging conditions for indicating one or more conditions that control the step of logging, wherein the plurality of logging conditions include a plurality of general conditions, a plurality of intermediary conditions, and a plurality of specific conditions; and

b. a plurality of sampling parameters for controlling a format of each recorded speech communication, wherein the plurality of sampling parameters include a first parameter for indicating a start of each recorded speech communication and a second parameter for indicating an end of each recorded speech communication.

3. The method according to claim 2 wherein the step of logging includes determining whether the plurality of general conditions require logging a current speech communication.

4. The method according to claim 3 wherein the step of logging further includes determining whether the plurality of intermediary conditions require logging the current speech communication.

5. The method according to claim 4 wherein the step of logging further includes determining whether the plurality of specific conditions require logging the current speech communication.

6. The method according to claim 1 wherein the step of logging includes storing each recorded speech communication in a first storage device while the user interacts with the speech recognition system.

7. The method according to claim 6 wherein the step of logging includes adding a first header to each recorded speech communication, wherein the first header includes a plurality of reference data.

8. The method according to claim 6 wherein the step of logging includes transferring each recorded speech communication to a second storage device after the user stops interacting with the speech recognition system.

9. The method according to claim 1 further including the step of providing a system statistics library for storing a plurality of operation data concerning operation of the speech recognition system.

10. The method according to claim 9 wherein the speech parameter block further includes a second data field for storing a plurality of reporting parameters that control whether the plurality of operation data should be updated.

11. The method according to claim 10 further including the step of updating the plurality of operation data as directed by the reporting parameters.

12. The method according to claim 10 further including the step of generating one or more performance records, each having a set of system performance statistics, wherein the step of generating is controlled by the plurality of reporting parameters.

13. The method according to claim 12 wherein the one or more performance records include a first detail level performance record, a second detail level performance record, a third detail level performance record, and a fourth detail level performance record, and wherein the plurality of reporting parameters determine which one of the one or more performance records is generated.

14. The method according to claim 12 further including the step of transferring the one or more performance records to a reporting system for facilitating system performance analysis.

15. A voice messaging system capable of recognizing one or more voice instructions from a user and capable of collecting system performance data, the voice messaging system comprising:

a. a speech parameter block library having a plurality of speech parameter blocks for regulating collection of system performance data, wherein each speech parameter block includes a data structure having a plurality of data fields, wherein the plurality of data fields includes a first data field for storing a plurality of logging parameters that control whether one or more speech communications between the voice messaging system and the user should be logged;

b. means coupled to the speech parameter block library for selecting an appropriate one of the plurality of speech parameter blocks to control collection of system performance data;

c. means coupled to the speech parameter block library for transparently monitoring the one or more speech communications via the plurality of logging parameters of the appropriate one of the plurality of speech parameter blocks; and

d. means coupled to the speech parameter block library for logging selective ones of the one or more speech communications as directed by the logging parameters, thereby forming a recorded speech communication to correspond with each of the one or more speech communications that is logged.

16. The voice messaging system according to claim 15 wherein the plurality of logging parameters include:

a. a plurality of logging conditions for indicating one or more conditions that control the means for logging, wherein the plurality of logging conditions include a plurality of general conditions, a plurality of intermediary conditions, and a plurality of specific conditions; and

b. a plurality of sampling parameters for controlling a format of each recorded speech communication, wherein the plurality of sampling parameters include a first parameter for indicating a start of each recorded speech communication and a second parameter for indicating an end of each recorded speech communication.

17. The voice messaging system according to claim 16 wherein the means for logging determines whether the plurality of general conditions require logging a current speech communication.

18. The voice messaging system according to claim 17 wherein the means for logging determines whether the plurality of intermediary conditions require logging the current speech communication.

19. The voice messaging system according to claim 18 wherein the means for logging determines whether the plurality of specific conditions require logging the current speech communication.

20. The voice messaging system according to claim 15 further comprising a first storage device, wherein the means for logging stores each recorded speech communication in the first storage device while the user interacts with the voice messaging system.

21. The voice messaging system according to claim 20 wherein the means for logging adds a first header to each recorded speech communication that is stored in the first storage device, wherein the first header includes a plurality of reference data.

22. The voice messaging system according to claim 20 further comprising a second storage device, wherein the means for logging transfers each recorded speech communication to the second storage device after the user stops interacting with the voice messaging system.

23. The voice messaging system according to claim 15 further including a system statistics library for storing a plurality of operation data concerning operation of the voice messaging system.

24. The voice messaging system according to claim 23 wherein each speech parameter block further includes a second data field for storing a plurality of reporting parameters that control whether the plurality of operation data should be updated.

25. The voice messaging system according to claim 24 further including means for updating the plurality of operation data as directed by the reporting parameters.

26. The voice messaging system according to claim 24 wherein the means for updating generates one or more performance records according to the plurality of reporting parameters, each performance record having a set of system performance statistics.

27. The voice messaging system according to claim 26 wherein the one or more performance records include a first detail level performance record, a second detail level performance record, a third detail level performance record, and a fourth detail level performance record, and wherein the plurality of reporting parameters determine which one of the one or more performance records is generated.

28. The voice messaging system according to claim 26 further including a reporting system for facilitating system performance analysis, wherein the means for updating transfers the one or more performance records to the reporting system.