System and methods for conducting an interactive dialog via a speech-based user interface

• US 7,461,000 B2
• Filed: 10/19/2004
• Issued: 12/02/2008
• Est. Priority Date: 10/19/2004
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Michelini, Vanessa V., Davis, Brent L., Polkosky, Melanie D.
• Primary Examiner(s): Hudspeth; David R.
• Assistant Examiner(s): Sked; Matthew J.
• Application Number:
  US10/968,594
• Publication Number:
  US 20060085192A1
• Time in Patent Office: 1,505 Days
• Field of Search: None
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A system and methods are provided for conducting an interactive dialog via a speech-based user interface. The system includes an auditory prompt module for generating a sequence of goal-directed auditory prompts based upon a pre-determined user-oriented task, and an error recovery module for responding to a communication error by initiating an error recovery based upon a user response to the sequence of goal-directed auditory prompts. The error recovery includes providing at least one error-recovery prompt selected from a hierarchy of error-recovery prompts, the selection based upon a hierarchy of communication error types.

Claims

1. A method for conducting a user dialog via a speech-based user interface, the method comprising:

providing a sequence of goal-directed auditory prompts, the sequence of goal-directed auditory prompts being based upon a pre-determined user-oriented task;

for each prompt, determining if there is a communication error; and

if a communication error occurs, responding to the communication error by initiating an error recovery including;

determining a type of the communication error from a hierarchy of communication error types based upon a sequential analysis of a user response to the particular prompt, the hierarchy of communication error types including an acoustical error, a lexical error, a syntactical error, and a conceptual error, wherein an acoustical error occurs when a volume at which the user response is provided is not within a predetermined audible range, wherein a lexical error occurs when there is no match between the user response and a list of pre-designated acceptable responses, wherein a syntactical error occurs when there is no match between parts of speech of the user response and expected parts of speech, and wherein a conceptual error occurs when a user fails to provide any auditory response within a predefined time interval or when the user response is not within an activated grammar corresponding to the sequence of goal-directed auditory prompts; and

providing at least one error-recovery prompt selected from a hierarchy of error-recovery prompts, the selection being based upon the determination of the type of communication error.

2. The method of claim 1, wherein the error recovery comprises:

if it is determined that an acoustical error has occurred, providing an acoustical error prompt in response thereto.

3. The method of claim 1, wherein the error recovery comprises:

if it is determined that a lexical error has occurred, providing a lexical error prompt in response thereto.

4. The method of claim 1, wherein the error recovery comprises:

if it is determined that a syntactical error has occurred, providing a syntactical error prompt in response thereto

5. The method of claim 1, wherein the error recovery comprises:

determining whether a conceptual error has occurred based upon a non-auditory user response within a predefined time period; and

if it is determined that a conceptual error has occurred, providing a conceptual error prompt in response thereto.

6. A system for conducting a user dialog via a speech-based user interface, the system comprising:

an auditory prompt module for generating a sequence of goal-directed auditory prompts, the sequence of goal-directed auditory prompts being based upon a pre-determined user-oriented task; and

an error recovery module for responding to a communication error by initiating an error recovery based upon a user response to a particular prompt of the sequence of goal-directed auditory prompts;

wherein the error recovery comprises;

determining a type of the communication error from a hierarchy of communication error types based upon a sequential analysis of a user response to the particular prompt, the hierarchy of communication error types including an acoustical error, a lexical error, a syntactical error, and a conceptual error, wherein an acoustical error occurs when a volume at which the user response is provided is not within a predetermined audible range, wherein a lexical error occurs when there is no match between the user response and a list of pre-designated acceptable responses, wherein a syntactical error occurs when there is no match between parts of speech of the user response and expected parts of speech, and wherein a conceptual error occurs when a user fails to provide any auditory response within a predefined time interval or when the user response is not within an activated grammar corresponding to the sequence of goal-directed auditory prompts; and

providing at least one error-recovery prompt sequentially selected from a hierarchy of error-recovery prompts, the sequential selection being based upon the determination of the type of communication error.

7. The system of claim 6, wherein the error recovery comprises:

if it is determined that an acoustical error has occurred, providing an acoustical error prompt in response thereto.

8. The system of claim 6, wherein the error recovery comprises:

if it is determined that a lexical error has occurred, providing a lexical error prompt in response thereto.

9. The system of claim 6, wherein the error recovery comprises:

if it is determined that a syntactical error has occurred, providing a syntactical error prompt in response thereto.

10. The system of claim 6, wherein the error recovery comprises:

if it is determined that a conceptual error has occurred, providing a conceptual error prompt in response thereto.

11. A computer-readable storage medium for conducting a user dialog via a speech-based user interface, the storage medium comprising computer instructions for:

providing a sequence of goal-directed auditory prompts, the sequence of goal-directed auditory prompts being based upon a pre-determined user-oriented task;

for each prompt, determining if there is a communication error; and

if a communication error occurs, responding to the communication error by initiating an error recovery including;

determining a type of the communication error from a hierarchy of communication error types based upon a sequential analysis of a user response to the particular prompt, the hierarchy of communication error types including an acoustical error, a lexical error, a syntactical error, and a conceptual error, wherein an acoustical error occurs when a volume at which the user response is provided is not within a predetermined audible range, wherein a lexical error occurs when there is no match between the user response and a list of pre-designated acceptable responses, wherein a syntactical error occurs when there is no match between parts of speech of the user response and expected parts of speech, and wherein a conceptual error occurs when a user fails to provide any auditory response within a predefined time interval or when the user response is not within an activated grammar corresponding to the sequence of goal-directed auditory prompts; and

providing at least one error-recovery prompt selected from a hierarchy of error-recovery prompts, the selection being based upon the determination of the type of communication error.