Methods and apparatus for adapting output speech in accordance with context of communication

• US 7,490,042 B2
• Filed: 03/29/2005
• Issued: 02/10/2009
• Est. Priority Date: 03/29/2005
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Picheny, Michael Alan, Eide, Ellen Marie, Hamza, Wael Mohamed
• Primary Examiner(s): ABEBE, DANIEL DEMELASH
• Application Number:
  US11/092,057
• Publication Number:
  US 20060229873A1
• Time in Patent Office: 1,414 Days
• Field of Search: 704/235, 704/257, 704/270, 704/275, 379/88.04, 715/708
• US Class Current: 704/270
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A technique for producing speech output in an automatic dialog system in accordance with a detected context is provided. Communication is received from a user at the automatic dialog system. A context of the communication from the user is detected in a context detector of the automatic dialog system. A message is created in a natural language generator of the automatic dialog system in communication with the context detector. The message is conveyed to the user through a speech synthesis system of the automatic dialog system, in communication with the natural language generator and the context detector. Responsive to a detected level of ambient noise, the context detector provides at least one command in a markup language to cause the natural language generator to create the message using maximally intelligible words and to cause the speech synthesis system to convey the message with increased volume and decreased speed.

Claims

1. A method of producing speech output in an automatic dialog system in accordance with a detected context, the method comprising the steps of:

receiving a communication from a user at the automatic dialog system;

detecting a context of the communication from the user in a context detector of the automatic dialog system, the context of the communication comprising an ambient noise level;

creating a message in a natural language generator of the automatic dialog system in communication with the context detector; and

conveying the message to the user through a speech synthesis system of the automatic dialog system, in communication with the natural language generator and the context detector; and

wherein, responsive to a detected level of ambient noise, the context detector provides at least one command in a markup language to cause the natural language generator to create the message using maximally intelligible words and to cause the speech synthesis system to convey the message with increased volume and decreased speed.

2. The method of claim 1, wherein the step of conveying the message to the user comprises the step of modifying articulation and pronunciation of the message to adapt the message in accordance with the detected context of the communication.

3. The method of claim 1, wherein the step of receiving a communication comprises the steps of:

transcribing words in the communication from the user in a speech recognition engine of the automatic dialog system;

determining the meaning of the words through a natural language understanding unit in communication with the speech recognition engine and the context detector in the automatic dialog system;

retrieving requested information in accordance with the meaning of the words, from a database in communication with the natural language understanding unit in the automatic dialog system; and

sending the requested information from the database to the text-to-speech system.

4. The method of claim 1, wherein the context of the communication further comprises at least one of an, an age of the user, a gender of the user, a location of user, a time of the communication, a date of the communication, and an emotional state of the user.

5. The method of claim 1, wherein the step of detecting a context of the communication comprises the steps of:

analyzing sound, words and meaning in the communication; and

determining the context of the communication based on the analysis.

6. An automatic dialog system for producing speech output in accordance with a detected context, comprising:

a context detector for detecting the context of a communication received from a user of the automatic dialog system, the context of the communication comprising an ambient noise level;

a natural language generator in communication with the context detector that creates the message; and

a speech synthesis system in communication with the natural language generator and the context detector, that conveys the message to the user;

wherein, responsive to a detected level of ambient noise, the context detector provides at least one command in a markup language to cause the natural language generator to create the message using maximally intelligible words and to cause the speech synthesis system to convey the message with increased volume and decreased speed.

7. The automatic dialog system of claim 6, wherein articulation and pronunciation is modified to adapt the message in accordance with the detected context of the communication.

8. The automatic dialog system of claim 6, further comprising:

a speech recognition engine that transcribes words in the communication from the user;

a natural language understanding unit in communication with the speech recognition engine and the context detector that determines the meaning of the words; and

a dialog manager in communication with the natural language understanding unit and the text-to-speech system that retrieves requested information from a database in accordance with the meaning of the words.

9. The automatic dialog system of claim 6, wherein the context of the communication further comprises at least one of an age of the user, a gender of the user, a location of user, a time of the communication, a date of the communication, and an emotional state of the user.

10. The automatic dialog system of claim 6, wherein the context detector analyzes noise, words and meaning in the communication and determines the context of the communication based on the analysis.