User adaptive system and control method thereof

• US 20060287850A1
• Filed: 06/08/2006
• Published: 12/21/2006
• Est. Priority Date: 02/03/2004
• Status: Active Grant

• Current Assignee: Sovereign Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Matsushita Electric Industrial Company Limited (Panasonic Holdings Corporation)
• Inventors: Morikawa, Koji
• Granted Patent: US 7,684,977 B2
• Time in Patent Office: Days
• US Class Current: 704/200
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

In an interface unit, an input section obtains an input signal of user'"'"'s speech or the like and an input processing section processes the input signal and detects information relating to the user. On the basis of the detection result, a response contents determination section determines response contents to the user. While, a response manner adjusting section adjusts a response manner to the user, such as speech speed and the like, on the basis of the processing state of the input signal, the information relating to the user detected from the input signal, and the like.

Claims

1. A user adaptive system comprising an interface unit which performs interaction with a user,

wherein the interface unit includes:

an input section for obtaining a speech of the user as a speech signal;

an input processing section for performing speech recognition of the speech signal obtained by the input section and for detecting speech contents of the user;

a response contents determination section for determining speech contents to the user on the basis of the speech contents of the user detected by the input processing section;

a response manner adjusting section for adjusting speech speed of the speech contents determined by the response contents determination section on the basis of user'"'"'s adaptation characteristic where speech speed of the user is changed upon influence of speech speed of the user adaptive system; and

an output section for outputting the speech contents determined by the response contents determination section at the speech speed adjusted by the response manner adjusting section.

2. The system of claim 1,

wherein the response manner adjusting section sets the speech speed of the user adaptive system to be higher than a target value when the speech speed of the user is lower than the target value or sets the speech speed of the user adaptive system to be lower than the target value when the speech speed of the user is higher than the target value.

3. The system of claim 2,

wherein the response manner adjusting section changes the speech speed of the user adaptive system so as to be close to the target value when the speech speed of the user becomes close to the target value.

5. The system of claim 1,

wherein the response manner adjusting section sets a target value of speech speed of the user to a value where the speech recognition exhibits optimum recognition performance.

6. The system of claim 1,

wherein the response manner adjusting section sets a target value of speech speed of the user to a value closer to the speech speed of the user than speech speed at which recognition performance of the speech recognition is optimum within a range where the recognition performance is obtained appropriately.

4. A controlling method for performing interaction with a user in a user adaptive system, comprising:

a first step of obtaining a speech of the user as a speech signal;

a second step of performing speech recognition of the speech signal obtained in the first step and detecting speech contents of the user;

a third step of determining speech contents to the user on the basis of the speech contents of the user detected in the second step;

a fourth step of adjusting speech speed of the speech contents determined in the third step on the basis of user'"'"'s adaptation characteristic where speech speed of the user is changed upon influence of speech speed of the user adaptive system; and

a fifth step of outputting the speech contents determined in the third step at the speech speed adjusted in the fourth step.