Analysis of the Temporal Evolution of Emotions in an Audio Interaction in a Service Delivery Environment

• US 20110196677A1
• Filed: 02/11/2010
• Published: 08/11/2011
• Est. Priority Date: 02/11/2010
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Dorai, Chitra, Visweswariah, Karthik, Joshi, Shailesh, Deshmukh, Om D., Verma, Ashish, Wright, Gary J., Rzasa, Maureen E., Zeng, Sai
• Granted Patent: US 8,417,524 B2
• Time in Patent Office: Days
• US Class Current: 704/246
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology

Abstract

According to one illustrative embodiment, a method is provided for analyzing an audio interaction. At least one change in an emotion of a speaker in an audio interaction and at least one aspect of the audio interaction are identified. The at least one change in an emotion is analyzed in conjunction with the at least one aspect to determine a relationship between the at least one change in an emotion and the at least one aspect, and a result of the analysis is provided.

Claims

1. A method in a data processing system for analyzing an audio interaction, comprising:

identifying at least one change in an emotion of a speaker in an audio interaction;

identifying at least one aspect of the audio interaction;

analyzing the at least one change in an emotion in conjunction with the at least one aspect to determine a relationship between the at least one change in an emotion and the at least one aspect; and

providing a result of the analysis.

2. The method of claim 1, wherein the speaker comprises a current speaker, further comprising:

identifying the current speaker in the audio interaction.

3. The method of claim 2, wherein identifying the current speaker in the audio interaction, comprises:

detecting a change in the speaker.

4. The method of claim 3, wherein detecting a change in the speaker comprises at least one of detecting prosodic features in the audio interaction, detecting lexical features in the audio interaction, and detecting channel-specific features in the audio interaction.

5. The method of claim 1, wherein identifying at least one change in an emotion of a speaker comprises at least one of detecting prosodic features of the audio interaction, detecting lexical features of the audio interaction, and identifying an interaction history of the speaker.

6. The method of claim 1, wherein the audio interaction is a telephone conversation.

7. The method of claim 1, wherein the audio interaction comprises an audio interaction between an agent in a contact center of an enterprise and a consumer.

8. The method of claim 7 further comprising:

collating the audio interaction with a plurality of further audio interactions to improve efficiency of the contact center.

9. The method of claim 7 further comprising:

analyzing a co-location of emotion changes and aspects over a plurality of audio interactions to propose best practices and to evaluate performance of agents in the contact center.

10. A computer program product in a computer recordable storage medium for analyzing an audio interaction in a data processing system, the computer program product having computer usable program code for:

identifying at least one change in an emotion of a speaker in an audio interaction;

identifying at least one aspect of the audio interaction;

analyzing the at least one change in an emotion in conjunction with the at least one aspect to determine a relationship between the at least one change in an emotion and the at least one aspect; and

providing a result of the analysis.

11. The computer program product of claim 10, wherein the speaker comprises a current speaker, further comprising computer usable program code for identifying the current speaker in the audio interaction.

12. The computer program product of claim 11, wherein the computer usable program code for identifying the current speaker in the audio interaction, comprises:

computer usable program code for detecting a change in the speaker.

13. The computer program product of claim 12, wherein the computer usable program codes for detecting a change in the speaker comprises computer usable program code for at least one of detecting prosodic features in the audio interaction, detecting lexical features in the audio interaction, and detecting channel-specific features in the audio interaction.

14. The computer program product of claim 10, wherein the computer usable program code for identifying at least one change in an emotion of the speaker comprises computer usable program code for at least one of detecting prosodic features of the audio interaction, detecting lexical features of the audio interaction, and identifying an interaction history of the speaker.

15. The computer program product of claim 10, wherein the audio interaction is a telephone conversation between an agent in a contact center of an enterprise and a consumer.

16. The computer program product of claim 15, and further comprising:

computer usable program code for collating the audio interaction with a plurality of further audio interactions.

17. An apparatus, comprising:

a memory storing instructions, and

at least one processing unit for executing the instructions for correlating performance events in a data processing system, the at least one processing unit executing the instructions to;

identify at least one change in an emotion of a speaker in an audio interaction;

identify at least one aspect of the audio interaction;

analyze the at least one change in an emotion in conjunction with the at least one aspect to determine a relationship between the at least one change in an emotion and the at least one aspect; and

provide a result of the analysis.

18. The apparatus of claim 17, wherein the speaker comprises a current speaker, the at least one processing unit further executing the instructions to identify the current speaker in the audio interaction.

19. The apparatus of claim 18, wherein the at least one processing unit executing the instructions to identify the current speaker, comprises the at least one processing unit executing the instructions to detect a change in the speaker.

20. The apparatus of claim 19, wherein the at least one processing unit executing the instructions to detect a change in the speaker, comprises the at least one processing unit executing the instructions to at least one of detect prosodic features in the audio interaction, detect lexical features in the audio interaction, and detect channel-specific features in the audio interaction.

21. The apparatus of claim 17, wherein the at least one processing unit executing the instructions to identify at least one change in an emotion of the speaker, comprises the at least one processing unit executing the instructions to detect prosodic features of the audio interaction, detect lexical features of the audio interaction, and identify an interaction history of the speaker.

22. The apparatus of claim 17, wherein the audio interaction is a telephone conversation between an agent in a contact center of an enterprise and a consumer.