System and method for a telephonic emotion detection that provides operator feedback

• US 6,480,826 B2
• Filed: 08/31/1999
• Issued: 11/12/2002
• Est. Priority Date: 08/31/1999
• Status: Expired due to Term

• Current Assignee: Accenture Global Services Limited (Accenture PLC)
• Original Assignee: Accenture LLP (Accenture PLC)
• Inventors: Pertrushin, Valery A.
• Primary Examiner(s): Chawan, Vijay B.
• Application Number:
  US09/387,621
• Publication Number:
  US 20020002464A1
• Time in Patent Office: 1,169 Days
• Field of Search: 704/270, 704/273-275
• US Class Current: 704/270
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

A system, method and article of manufacture are provided for monitoring emotions in voice signals and providing feedback thereon. First, a voice signal is received representative of a component of a conversation between at least two subjects. Thereafter, an emotion associated with the voice signal is determined. Feedback then provided to a third party based on the determined emotion.

Claims

1. A method for monitoring emotions in voice signals and providing feedback thereon comprising the steps of:

(a) receiving a voice signal representative of a component of a conversation between at least two human subjects;

(b) extracting a predetermined segment of audio frequency from the voice signal;

(c) determining an emotion associated with said voice signal by using said predetermined segment of audio frequency as an input to a neural network containing at least one algorithm that is used to determine said emotion; and

(d) providing feedback to a third party based on the emotion that is determined from said segment of audio frequency being input to said neural network.

2. A method as recited in claim 1, wherein the conversation is carried out over a telecommunications network.

3. A method as recited in claim 2, wherein one of the subjects is a customer, one of the subjects is an employee, and the third party is a manager.

4. A method as recited in claim 3, wherein the employee is employed by a call center.

5. A method as recited in claim 1, wherein the feedback is provided only if the emotion is determined to be a negative emotion selected from the group of negative emotions consisting of anger, sadness, and fear.

6. A computer program embodied on a computer readable medium for monitoring emotions in voice signals and providing feedback thereon comprising:

(a) a code segment that receives a voice signal representative of a component of a conversation between at least two human subjects;

(b) a code segment that extracts a predetermined segment of audio frequency from the voice signal;

(c) a code segment that determines an emotion associated with the voice signal by using said predetermined segment of audio frequency as an input to a neural network containing at least one algorithm that is used to determine said emotion; and

(d) a code segment that provides feedback to a third party based on the emotion that is determined from said segment of audio frequency being input to said neural network.

7. A computer program as recited in claim 6, wherein the conversation is carried out over a telecommunications network.

8. A computer program as recited in claim 7, wherein one of the subjects is a customer, one of the subjects is an employee, and the third party is a manager.

9. A computer program as recited in claim 8, wherein the employee is employed by a call center.

10. A computer program as recited in claim 6, wherein the feedback is provided only if the emotion is determined to be a negative emotion selected from the group of negative emotions consisting of anger, sadness, and fear.

11. A system for monitoring emotions in voice signals and providing feedback thereon comprising:

(a) logic that receives a voice signal representative of a component of a conversation between at least two human subjects;

(b) logic that extracts at least one predetermined segment of audio frequency from the voice signal;

(c) logic that determines an emotion associated with the voice signal by using said at least one predetermined segment of audio frequency as an input to a neural network containing at least one algorithm that is used to determine said emotion; and

(d) logic that provides feedback to a third party based on the emotion that is determined from said segment of audio frequency being input to said neural network.

12. A system as recited in claim 11, wherein the conversation is carried out over a telecommunications network.

13. A system as recited in claim 12, wherein one of the subjects is a customer, one of the subjects is an employee, and the third party is a manager.

14. A system as recited in claim 13, wherein the employee is employed by a call center.

15. A system as recited in claim 11, wherein the feedback is provided only if the emotion is determined to be a negative emotion selected from the group of negative emotions consisting of anger, sadness, and fear.

16. A method for monitoring emotions in voice signals and providing feedback thereon comprising the steps of:

(a) receiving a voice signal representative of a component of a conversation between at least two human subjects;

(b) extracting at least one predetermined segment of audio frequency from the voice signal;

(c) determining an emotion associated with the voice signal by using said at least one predetermined segment of audio frequency as an input to an ensemble of classifiers that are used to determine said emotion; and

(d) providing feedback to a third party based on the emotion that is determined from said segment of audio frequency being input to said ensemble of classifiers.