Method for recognizing speech/speaker using emotional change to govern unsupervised adaptation

• US 20030154076A1
• Filed: 02/11/2003
• Published: 08/14/2003
• Est. Priority Date: 02/13/2002
• Status: Active Grant

• Current Assignee: Sony Deutschland GmbH (Sony Group Corp.)
• Original Assignee: Sony Deutschland GmbH (Sony Group Corp.)
• Inventors: Kemp, Thomas
• Granted Patent: US 7,684,984 B2
• Time in Patent Office: Days
• US Class Current: 704/236
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

To improve the performance and the recognition rate of a method for recognizing speech in a dialogue system, or the like, it is suggested to derive emotion information data (EID) from speech input (SI) being descriptive for an emotional state of a speaker or a change thereof based upon which a process of recognition is chosen and/or designed.

Claims

1. Method for recognizing speech/speaker in a dialogue system, or the like,

wherein speech input (SI) of at least one speaker is received,

wherein a process of recognition based on said speech input (SI) is performed,

emotion information data (EID) being descriptive for an emotional state of a speaker or a change thereof are derived from said speech input (SI) or from parts thereof, and

wherein said process of recognition is chosen and/or designed and/or modified based on said emotion information data (EID).

2. Method according to claim 1,

wherein the step of choosing and/or designing the process of recognition is performed after given numbers of recognition results and in particular after each single recognition result.

3. Method according to any one of the preceding claims,

wherein the step of choosing and/or designing the process of recognition includes a step of selecting acoustic models (AM1, AM2), or the like and/or sets thereof to be involved in the recognition process.

4. Method according to any one of the preceding claims,

wherein said emotion information data (EID) are generated so as to reflect emotional states of a given speaker before and after a recognition result is presented and/or a system action (SA) in response to the recognition result is performed.

5. Method according to any one of the preceding claims,

wherein a first set of acoustic models is selected for the process of recognition until said emotion information data (EID) show a predetermined emotional shift of a speaker, upon which a second set of acoustic models is selected.

6. Method according to claim 5,

wherein a negative shift is used as said predetermined emotional shift.

7. Method according to any one of the claims 5 or 6,

wherein shifts to anger, disappointment, and/or the like are used as said emotional shifts.

8. Method according of any one of the claims 5 to 7,

wherein speaker-adapted or speaker-adaptable acoustic models are involved in said first set (AM2) of acoustic models.

9. Method according to anyone of the claims 5 to 8,

wherein speaker-independent acoustic models are involved in said second set (AM1) of acoustic models.

10. Method according to any one of the preceding claims,

wherein said process of recognition at least includes a sub-process of recognizing speech.

11. Method according to any one of the preceding claims,

wherein said process of recognition at least includes a sub-process of recognizing a speaker.

12. Method for operating a dialogue system or the like in which a method for recognizing speech/speaker according to any one of the claims 1 to 11 is involved.

13. Dialogue system which is capable of realizing a method for recognizing speech/speaker according to any one of the claims 1 to 11 and/or the method for operating a dialogue system according to claim 12, and/or the steps thereof.

14. Computer program product, comprising computer program means adapted to perform and/or to realize the method for recognizing speech/speaker according to any one of the claims 1 to 11 and/or the method for operating a dialogue system according to claim 12, or the steps thereof, when it is executed on a computer, a digital signal processing means, and/or the like.