Speech communiction system and method, and robot apparatus

• US 20050043956A1
• Filed: 07/02/2004
• Published: 02/24/2005
• Est. Priority Date: 07/03/2003
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Aoyama, Kazumi, Shimomura, Hideki
• Granted Patent: US 8,209,179 B2
• Time in Patent Office: Days
• US Class Current: 704/276
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

This invention realizes a speech communication system and method, and a robot apparatus capable of significantly improving entertainment property. A speech communication system with a function to make conversation with a conversation partner is provided with a speech recognition means for recognizing speech of the conversation partner, a conversation control means for controlling conversation with the conversation partner based on the recognition result of the speech recognition means, an image recognition means for recognizing the face of the conversation partner, and a tracking control means for tracing the existence of the conversation partner based on one or both of the recognition result of the image recognition means and the recognition result of the speech recognition means. The conversation control means controls conversation so as to continue depending on tracking of the tracking control means.

Claims

1. A speech communication system with a function to have conversation with a conversation partner, comprising:

speech recognition means for recognizing speech of the conversation partner;

conversation control means for controlling conversation with the conversation partner based on a recognition result of the speech recognition means;

image recognition means for recognizing a face of the conversation partner; and

tracking control means for tracking existence of the conversation partner based on one or both of a recognition result of the image recognition means and a recognition result of the speech recognition means, wherein

the conversation control means continues the conversation in keeping with tracking of the tracking control means.

2. The speech communication system according to claim 1, wherein

the conversation control means continues the conversation when speech contents of the conversation partner obtained as a recognition result of the speech recognition means are the same as predicted response contents even if the tracking control means fails the tracking.

3. The speech communication system according to claim 2, wherein

the conversation control means finishes the conversation when the response contents cannot be obtained from the conversation partner even if a notification is repeated to urge the conversation partner to make the response contents a prescribed number of times in a case where the tracking control means fails the tracking and the speech contents of the conversation partner are not the same as the predicted response contents.

4. The speech communication system according to claim 3, wherein

the conversation control means makes a notification to urge the conversation partner to make the response contents when speech of the conversation partner cannot be obtained for a prescribed period of time.

5. The speech communication system according to claim 1, comprising

contact recognition means for recognizing contacts of the conversation partner, wherein

the tracking control means tracks the existence of the conversation partner based on a certain combination of the recognition result of the speech recognition means, the recognition result of the image recognition means, and a recognition result of the contact recognition means.

6. The speech communication system according to claim 5, wherein

the conversation control means continues the conversation when the recognition result of the contact recognition means indicates existence of a contact of the conversation partner even if the tracking control means fails the tracking.

7. The speech communication system according to claim 5, wherein

the conversation control means continues the conversation when a contact of the conversation partner can be confirmed as the recognition result of the contact recognition means after a notification to ask the conversation partner to touch the contact recognition means is made just before the conversation is controlled so as to finish, in a case where the response contents cannot be obtained after a notification to urge the conversation partner to make the response contents is made a prescribed number of times in a case where the tracking control means fails the tracking and the speech contents of the conversation partner are not the same as the predicted response contents.

8. A speech communication method with a function to have conversation with a conversation partner, comprising:

a first step of tracking existence of the conversation partner based on one or both of a speech recognition result obtained by recognizing speech of the conversation partner and a image recognition result obtained by recognizing a face of the conversation partner; and

a second step of continuing conversation with the conversation partner obtained as the speech recognition result in keeping with the tracking.

9. The speech communication method according to claim 8, wherein,

in the second step, the conversation is continued when speech contents of the conversation partner obtained as the speech recognition result are the same as predicted response contents even if the tracking cannot be performed in the first step.

10. The speech communication method according to claim 9, wherein,

in the second step, the conversation is finished when the response contents cannot be obtained from the conversation partner even if a notification to urge the conversation partner to make the response contents is made a prescribed number of times, in a case where the tracking cannot be performed in the first step and the speech contents of the conversation partner are not the same as the predicted response contents.

11. The speech communication method according to claim 10, wherein,

in the second step, a notification to urge the conversation partner to make the response contents is made when speech of the conversation partner cannot be obtained for a prescribed period of time.

12. The speech communication method according to claim 8, wherein,

in the first step, the existence of the conversation partner is tracked based on a certain combination of the speech recognition result, the image recognition result, and a contact recognition result obtained by recognizing contacts of the conversation partner.

13. The speech communication method according to claim 12, wherein,

in the second step, the conversation is continued when a contact of the conversation partner is confirmed as the contact recognition result even if the tracking cannot be performed in the first step.

14. The speech communication method according to claim 12, wherein,

in the second step, the conversation is continued when a contact of the conversation partner is confirmed as the contact recognition result after a notification to ask the conversation partner to touch the contact recognition is made just before the conversation is controlled so as to finish, even if the response contents cannot be obtained from the conversation partner after a notification to urge the conversation partner to make the response contents is made a prescribed number of times in a case where the tracking cannot be performed in the first step and the speech contents of the conversation partner are not the same as the predicted response contents.

15. A robot apparatus having a speech communication system with a function to have conversation with a conversation partner, comprising:

speech recognition means for recognizing speech of the conversation partner;

conversation control means for controlling conversation with the conversation partner based on a recognition result of the speech recognition means;

image recognition means for recognizing a face of the conversation partner; and

tracking control means for tracking existence of the conversation partner based on one or both of a recognition result of the image recognition means and a recognition result of the speech recognition means, wherein

the conversation control means continues the conversation in keeping with tracking of the tracking control means.