Communicating across voice and text channels with emotion preservation

• US 20070208569A1
• Filed: 03/03/2006
• Published: 09/06/2007
• Est. Priority Date: 03/03/2006
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Srinivasan, Deepa, Subramanian, Balan, Salahshoor, Mohamad
• Granted Patent: US 7,983,910 B2
• Time in Patent Office: Days
• US Class Current: 704/270
• CPC Class Codes: G10L 13/04 Details of speech synthesis systems, e.g. synthesiser structure or memory management
• CPC Class Codes: G10L 19/0018 Speech coding using phonetic or linguistical decoding of the source; Reconstruction using text-to-speech synthesis

Abstract

Emotion across voice and text communication channels are abstracted, preserved and translated. A voice communication is received and analyzed for emotion content. The textual content of the communication is realized summarily using word recognition techniques. The textual content is then analyzed for emotion content. Words and phrases derived from the word recognition are compared emotion words and phrases in a text mine database. The emotion from the two analyses is then used for marking up the textual content as emotion metadata. The text and emotion markup abstraction for a voice communication can also be translated into a using text and emotion translation definitions. The translated emotion metadata is used to emotion mine words that have an emotion connotation in the culture of the second language. Those words are then substituted for corresponding words in the translated text. The translated text and emotion words are modulated into a synthesized voice and the delivery is adjusted using emotion voice patterns derived from the translated emotion metadata. Additionally, text and emotion markup abstractions can be archived as artifacts of their original voice communication and then be searched using emotion conditions for the context of the original communication. A search query includes for communication artifact includes an emotion value and a context value that are used to sort the database artifacts. Result artifacts that contain matching emotion metadata, within the context constraint, are passed to the requestor for review.

Claims

1. A computer program product for communicating across channels with emotion preservation, said computer program product comprising:

a computer usable medium having computer useable program code embodied therewith, the computer usable program code comprising;

computer usable program code to receive a voice communication;

computer usable program code to analyze the voice communication for first emotion content;

computer usable program code to analyze textual content of the voice communication for second emotion content; and

computer usable program code to mark up the textual content with emotion metadata for one of the first emotion content and the second emotion content.

2. The computer program product recited in claim 1 further comprising:

computer usable program code to analyze the voice communication for textual content.

3. The computer program product recited in claim 2, wherein the computer usable program code to analyze the textual content of the voice communication for second emotion content further comprises:

computer usable program code to obtain at least one word of the textual content;

computer usable program code to access a plurality of text-to-emotion definitions; and

computer usable program code to compare the at least one word from the textual content to the plurality of text-to-emotion definitions.

4. The computer program product recited in claim 3 further comprising:

computer usable program code to obtain one of a word phrase, punctuation, lexicon and syntax of the textual content;

computer usable program code to access a plurality of text-to-emotion definitions; and

computer usable program code to compare the one of a word phrase, punctuation, lexicon and syntax to the plurality of text-to-emotion definitions.

5. The computer program product recited in claim 2, wherein computer usable program code to analyze the voice communication for first emotion content further comprises:

computer usable program code to assess the second emotion content; and

computer usable program code to select a voice analysis model based on the assessment of the emotion content.

6. The computer program product recited in claim 2, wherein computer usable program code to mark up the textual content with emotion metadata for one of the first emotion content and the second emotion content further comprises:

computer usable program code to compare the first emotion content and the second emotion content; and

computer usable program code to identify the one of the first emotion content and the second emotion based on the comparison of the first emotion content and the second emotion content.

7. The computer program product recited in claim 2, wherein the computer usable program code to mark up the textual content with emotion metadata for one of the first emotion content and the second emotion content further comprises:

computer usable program code to rank the analysis of the voice communication based on an attribute of the analysis of the voice communication;

computer usable program code to rank the analysis of the textual content based on an attribute of the analysis of the textual content; and

computer usable program code to identify the one of the first emotion content and the second emotion based on the ranking of the analysis of the voice communication and the ranking of analysis of the textual content.

8. The computer program product recited in claim 7, wherein the attribute of the analysis of the voice communication and the attribute of the analysis of the textual content is one of accuracy of the respective analysis and operating efficiency.

9. The computer program product recited in claim 3, further comprising:

computer usable program code to select a plurality of voice pattern-to-emotion definitions based on a language for the voice communication, a dialect for the voice communication and a speaker for the voice communication; and

computer usable program code to select a plurality of text-to-emotion definitions based on a language for the voice communication, a dialect for the voice communication and a speaker for the voice communication.

10. The computer program product recited in claim 9, wherein the voice pattern-to-emotion definitions comprises voice patterns for one of pitch, tone, cadence and amplitude.

11. The computer program product recited in claim 3, further comprising:

computer usable program code to select a plurality of text-to-emotion definitions based on a speaker for the voice communication, an audience for the speaker of the voice communication and the circumstance of the voice communication; and

computer usable program code to select a plurality of voice pattern-to-emotion definitions based on a speaker for the voice communication, an audience for the speaker of the voice communication and the circumstance of the voice communication.

12. A computer program product for communicating across channels with emotion preservation, said computer program product comprising:

a computer usable medium having computer useable program code embodied therewith, the computer usable program code comprising;

computer usable program code to receive a first language communication comprising text marked up with emotion metadata;

computer usable program code to translate the emotion metadata into second language emotion metadata;

computer usable program code to translate the text to second language text;

computer usable program code to analyze the second language emotion metadata for second language emotion information; and

computer usable program code to combine the second language emotion information in first language communication with the second language text.

13. The computer program product recited in claim 12, wherein the second language emotion information is one of text, phrase, punctuation, lexicon or syntax.

14. The computer program product recited in claim 13, further comprising:

computer program product to voice synthesize the second language text and the second language emotion text; and

computer program product to adjust the synthesized voice with the second language emotion metadata.

15. The computer program produce recited in claim 13, wherein the computer program product to analyze the second language emotion metadata for second language emotion information further comprises:

computer program product to receive at least one second language emotion metadatum;

computer program product to access a plurality of voice emotion-to-text pattern definition, said plurity of voice emotion-to-text pattern definitions being based on the second language; and

computer program product to compare the at least one second language emotion metadatum to the plurity of voice emotion-to-text pattern definitions.

16. The computer program product recited in claim 15, further comprising:

computer program product to select the plurality of voice emotion-to-text pattern definitions are based on the second language.

17. The computer program product recited in claim 15, wherein the-computer program product to adjust the synthesized voice with the second language emotion metadata further comprises:

computer program product to receive at least one second language emotion metadatum;

computer program product to access a plurality of emotion-to-voice pattern definitions, wherein the voice patterns comprises one of pitch, tone, cadence and amplitude;

computer program product to match the at least one second language emotion metadatum to one of the plurality of emotion-to-voice pattern definitions, said plurality of emotion-to-voice pattern definitions being based on the second language; and

computer program product to alter a synthesized voice pattern of the synthesized voice with a voice pattern corresponding to the matching emotion-to-voice pattern definition.

18. A computer program product for communicating across channels with emotion preservation, said computer program product comprising:

a computer usable medium having computer useable program code embodied therewith, the computer usable program code comprising;

computer usable program code to receive a query for a communication artifact from a requester, said artifact representing a voice communication as textual content with markup emotion metadata;

computer usable program code to parse a context value from the query;

computer usable program code to parse an emotion value from the query;

computer usable program code to sort a plurality of communication artifact records based on the context value;

computer usable program code to identify at least one communication artifact record by the context value;

computer usable program code to sort the at least one identified communication artifact record by the emotion value;

computer usable program code to identify at least one result communication artifact; and

computer usable program code to forward the identified at least one result communication artifact to the requestor.

19. The computer program product recited in claim 18, wherein the context value relates to the context of the communication.

20. The computer program product recited in claim 18, wherein the emotion value relates to the emotion metadata of the artifact.

21. The computer program product recited in claim 18 further comprising:

computer usable program code to mark a portion of the identified at least one result communication artifact with emotion metadata consistent with the emotion value of the query.

22. The computer program product recited in claim 18 further comprising:

computer usable program code to receive a second query for a communication artifact from the requestor;

computer usable program code to parse a context value from the second query;

computer usable program code to parse an updated emotion value from the second query;

computer usable program code to identify at least one update result communication artifact record by one of the updated emotion value and the updated context value; and

computer usable program code to forward the identified at least one updated result communication artifact to the requester.

23. A method for communicating across channels with emotion preservation, comprising:

receiving a voice communication;

analyzing the voice communication for first emotion content;

analyzing textual content of the voice communication for second emotion content; and

marking up the textual content with emotion metadata for one of the first emotion content and the second emotion content.

24. The method recited in claim 23 further comprising:

analyzing the voice communication for textual content.

25. The method recited in claim 24, wherein analyzing the voice communication for textual content further comprises:

extracting voice patterns from the voice communication;

accessing a plurality of voice pattern-to-text definitions; and

comparing the extracted voice patterns to the plurality of voice pattern-to-text definitions; and

analyzing the textual content of the voice communication for second emotion content further comprises;

obtaining at least one word of the textual content;

accessing the plurality of text-to-emotion definitions; and

comparing the at least one word from the textual content to the plurality of text-to-emotion definitions.