Speech-responsive voice messaging system and method

• US 6,539,078 B1
• Filed: 02/14/2000
• Issued: 03/25/2003
• Est. Priority Date: 03/24/1997
• Status: Expired due to Term

• Current Assignee: Avaya Incorporated
• Original Assignee: Avaya Incorporated
• Inventors: Hunt, Peter, Grajski, Kamil, Rub, Leonardo, Albright, Susannah
• Primary Examiner(s): WEAVER, SCOTT LOUIS
• Application Number:
  US09/504,059
• Time in Patent Office: 1,135 Days
• Field of Search: 379/88.01, 379/88.02, 379/88.03, 379/88.04, 379/88.22, 379/88.24, 704/200, 704/231, 704/251, 704/252, 704/270, 704/275
• 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. An automated system for recognizing an input from a user in response to an interrogatory provided by the automated system, the automated system comprising:

a. a template library for storing a plurality of speech templates, each corresponding to one of a plurality of commands available for the user; and

b. a first controller coupled to the template library and configured to match the input with one or more of the plurality of speech templates, thereby forming a set of candidate results, wherein each candidate result indicates existence of a potential match between one of the plurality of commands and the input, wherein the input is one selected from a group consisting of a voice input corresponding to a speech command structure and a dual tone multi-frequency signal input corresponding to a dual tone multi-frequency command structure, wherein the speech command structure is different than the dual tone multi-frequency command structure, further wherein if the input is the voice input, then the first controller invokes one of the plurality of commands that corresponds to the voice input, and if the input is the dual tone multi-frequency signal input, then the first controller invokes one of the plurality of commands that corresponds to the dual tone multi-frequency input.

2. The automated system according to claim 1 wherein the plurality of speech templates include at least one user dependent speech template and at least one user independent speech template.

3. The automated system according to claim 1 further comprising a command selector coupled to the template library and the first controller, wherein the command selector is configured to selectively identify from the set of candidate results a best candidate result and is configured to invoke a best command corresponding to the best candidate result.

4. The automated system according to claim 1 wherein the plurality of speech templates include a plurality of user independent speech templates.

5. The automated system according to claim 1 wherein the plurality of speech templates include a plurality of user dependent speech templates.

6. The automated system according to claim 1 wherein the first controller invokes one of the plurality of commands that corresponds to the dual tone multi-frequency input by transferring the input to a second controller if the input is the dual tone multi-frequency signal input, wherein the second controller is configured to process the dual tone multi-frequency signal input and to invoke one of the plurality of commands that corresponds to the dual tone multi-frequency signal input.

7. A voice messaging system capable of recognizing an input from a user in response to an interrogatory generated by the voice messaging system, the voice messaging system comprising:

a. a template library for storing a plurality of speech templates, each corresponding to one of a plurality of commands available for the user;

b. a first controller coupled to the template library and configured to match the input with one or more of the plurality of speech templates, thereby forming a set of candidate results, wherein each candidate result indicates existence of a potential match between one of the plurality of commands and the input, wherein the input is one selected from a group consisting of a voice input and a dual tone multi-frequency signal input; and

c. a second controller configured to process the dual tone multi-frequency signal input and to invoke one of the plurality of commands that corresponds to the dual tone multi-frequency signal input, wherein the first controller transfers the input to the second controller if the input is the dual tone multi-frequency signal input.

8. The voice messaging system according to claim 7 wherein the plurality of speech templates include at least one user dependent speech template and at least one user independent speech template.

9. The voice messaging system according to claim 7 wherein the plurality of speech templates include a plurality of user independent speech templates.

10. The voice messaging system according to claim 7 wherein the plurality of speech templates include a plurality of user dependent speech templates.

11. The voice messaging system according to claim 7 further comprising a command selector coupled to the template library and the first controller, wherein the command selector is configured to selectively identify from the set of candidate results a best candidate result and is configured to invoke a best command corresponding to the best candidate result.