Speech-responsive voice messaging system and method

• US 6,094,476 A
• Filed: 03/24/1997
• Issued: 07/25/2000
• Est. Priority Date: 03/24/1997
• Status: Expired due to Term

• Current Assignee: Avaya Incorporated
• Original Assignee: Octel Communications Corp. (Nokia Corporation)
• Inventors: Hunt, Peter, Grajski, Kamil, Rub, Leonardo, Albright, Susannah
• Primary Examiner(s): WEAVER, SCOTT LOUIS
• Application Number:
  US08/822,034
• Time in Patent Office: 1,219 Days
• Field of Search: 379/88.01, 379/88.03, 379/88.04, 704/200, 704/231, 704/251, 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. A method for speech-responsive voice messaging comprising the steps of:

a. generating a set of candidate results, each candidate result corresponding to a potential match between a command and a response from a user, wherein each candidate result includes a candidate command and at least one score corresponding to the candidate command;

b. evaluating the quality of the candidate results according to a plurality of quality thresholds applied to each score; and

c. invoking one from a group of a speech user interface navigation operation and a voice messaging operation according to the quality of the candidate result evaluation.

2. The method according to claim 1 further comprising the step of confirming that the potential match between the command and the response is correct when the quality of the candidate results are below the plurality of thresholds.

3. The method according to claim 1 further comprising the step of identifying a vocabulary set corresponding to a plurality of available commands.

4. The method according to claim 1 wherein the set of candidate results includes at least one speaker independent command.

5. The method according to claim 1 wherein the set of candidate results includes at least one speaker dependent command.

6. The method according to claim 1 wherein the response is one from a group of an utterance and a dual tone multi-frequency input, and further wherein the step of generating includes transferring the user to a dual tone multi-frequency module configured to process the dual tone multi-frequency input when the response is the dual tone multi-frequency input.

7. The method according to claim 6 wherein the step of generating further includes receiving the utterance.