Methods and apparatus for voice recognition for call treatment modification on messaging

• US 8,108,218 B1
• Filed: 12/13/1999
• Issued: 01/31/2012
• Est. Priority Date: 12/13/1999
• Status: Expired due to Term

• Current Assignee: Avaya Incorporated
• Original Assignee: Avaya Incorporated
• Inventors: Huboi, Peter Allen
• Primary Examiner(s): Godbold, Douglas
• Application Number:
  US09/459,380
• Time in Patent Office: 4,432 Days
• Field of Search: 704/275, 704/251, 704/271, 379/88.01, 379/88.04
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

Methods and systems for analyzing voice information to determine if specific words or phrases are used or if the voice information exhibits a particular pattern of speech. Depending on which words or phrases are determined to have been used, a specific action or actions is taken. The words or phrases along with the actions may be user specified. In one example, a voice message is analyzed to determine if it includes any of the specified words or phrases or whether it exhibits a particular pattern of speech. If so, a specified action, such as forwarding the voice message to a particular person, is performed. In another example, voice information from a called person is analyzed to gain information regarding the status of a call. This information may be used, for example, for generating call statistics or notifying a supervisor on the status of a call.

Claims

1. A method for processing a voice message, comprising:

storing one or more voice representations, wherein each voice representation corresponds to a word or phrase and is associated with a value;

storing one or more actions;

receiving a voice message;

receiving a one of;

a user-specified word and a user-specified phrase from a user, the received user-specified word or phrase corresponding to a word or phrase having a corresponding stored voice representation;

analyzing the voice message to determine if one or more of the stored voice representations corresponding to the received user-specified word or phrase occur in the voice message and to generate a final criteria measurement value associated with the voice message, the final criteria measurement value based on the value associated with each determined stored voice representation occurring in the voice message; and

performing one or more of the stored actions based on the final criteria measurement value if one or more of the stored voice representations are found to occur in the voice message.

2. The method of claim 1, wherein each of the stored voice representations is a phoneme representation of a word or phrase.

3. The method of claim 2, wherein the received voice message is an analog voice message, the method further comprising:

converting the analog voice message from analog to digital; and

processing the digitized voice message into phonemes;

wherein analyzing the voice message to determine if one or more of the stored voice representations are used includes comparing the phonemes from the voice message with one or more of the stored voice representations.

4. The method of claim 1, further comprising:

the user specifying one or more actions, wherein the actions are to be performed in the event one or more of the voice representations are found in the voice message;

storing the user specified one or more actions; and

wherein in performing one or more of the stored actions, the stored actions include the user specified actions.

5. The method of claim 1, wherein the stored one or more actions include marking the message as urgent.

6. The method of claim 1, wherein the stored one or more actions include calling a pager.

7. The method of claim 1, wherein the stored one or more actions include forwarding the voice message.

8. The method of claim 1, wherein the voice message is received over a telephone line.

9. A method for analyzing voice information received from a person over a communications line, comprising:

storing one or more voice representations, where each voice representation corresponds to a word or phrase and is associated with a value;

storing one or more actions;

receiving voice information from a person over a communications line;

receiving a one of;

a user-specified word and a user-specified phrase from a user, the received user-specified word or phrase corresponding to a word or phrase having a corresponding stored voice representation;

analyzing the voice information from the person to determine if one or more of the stored voice representations corresponding to the received user-specified word or phrase occur in the voice information received from the person and to generate a final criteria measurement value associated with the voice information, the final criteria measurement value based on the value associated with each determined stored voice representation occurring in the voice information; and

performing one or more of the stored actions based on the final criteria measurement value if the voice information is found to include one or more of the stored voice representations.

10. The method of claim 9, wherein each of the stored voice representations is a phoneme representation of a word or phrase.

11. The method of claim 10, wherein the received voice information is analog voice information, the method further comprising:

converting the analog voice information from analog to digital; and

processing the digitized voice information in phonemes;

wherein analyzing the voice information to determine if one or more of the stored voice representations are used includes comparing the phonemes from the voice information with one or more of the stored voice representations.

12. The method of claim 9, further comprising:

the user specifying one or more actions, wherein the actions are to be performed in the event one or more of the stored voice representations are found in the voice information;

storing the user specified actions; and

wherein in performing one or more of the stored actions, the stored actions include the user specified actions.

13. The method of claim 9, wherein:

receiving voice information comprises receiving voice information during a call; and

the one or more actions include compiling statistics on the call.

14. The method of claim 9, wherein the communications line is a telephone line.

15. An apparatus for processing a voice message, comprising:

a storage device for storing one or more voice representations where each voice representation corresponds to a word or phrase and is associated with a criteria measurement value, and for storing one or more actions;

an interface for receiving from a user a one of;

a user-specified word and a user-specified phrase; and

a processor for receiving a voice message, analyzing the voice message to determine if one or more of the stored voice representations corresponding to the received user-specified word or phrase occur in the voice message and to generate a final criteria measurement value associated with the voice message, and performing one or more of the stored actions based on the final criteria measurement value if one or more of the stored voice representations are found to occur in the voice message, the final criteria measurement value based on the value associated with each determined stored voice representation occurring in the voice message.

16. The apparatus of claim 15, wherein each of the voice representations is a phoneme representation of a word or phrase.

17. The apparatus of claim 16, further comprising:

an analog to digital converter for converting an analog voice message from analog to digital; and

wherein the processor is further for processing the digitized voice message into phonemes and comparing the phonemes from the voice message with one or more of the stored voice representations.

18. The apparatus of claim 15, further comprising:

a user interface for receiving user specified actions, wherein the actions are to be performed in the event one or more of the stored voice representations are found in the voice message; and

wherein the storage device is further for storing the user specified actions.

19. The apparatus of claim 15, wherein the apparatus is connected to a telephone line, and the processor is capable of receiving the voice message over the telephone line.

20. An apparatus for analyzing voice information received from a person over a communications line, comprising:

a storage device for storing one or more voice representations, where each voice representation corresponds to a word or phrase and is associated with a value, and for storing one or more actions;

an interface for receiving a one of;

a user-specified word and a user-specified phrase; and

a processor for receiving voice information from a person over a communications line, analyzing the voice information to determine if one or more of the stored voice representations corresponding to the received user-specified word or phrase occur in the voice information received from the person and to generate a final criteria measurement value associated with the voice information, and performing one or more of the stored actions based on the final criteria measurement value if the voice information is found to include one or more of the stored voice representations, the final criteria measurement value based on the value associated with each determined stored voice representation occurring in the voice information.

21. The apparatus of claim 20, wherein each of the voice representations is a phoneme representation of a word or phrase.

22. The apparatus of claim 21, wherein the received voice information is analog voice information, further comprising:

an analog to digital converter for converting the analog voice information from analog to digital; and

wherein the processor is further for processing the digitized voice information into phonemes and comparing the phonemes from the voice information with one or more of the stored voice representations.

23. The apparatus of claim 20, further comprising:

a user interface for receiving information regarding user specified actions, wherein the actions are to be performed in the event one or more of the voice representations are found in the voice information; and

wherein the storage device is further for storing the user specified actions.

24. The apparatus of claim 20, wherein:

the voice information is received during a call; and

the one or more actions include compiling statistics on the call.

25. The apparatus of claim 20, wherein the processor is capable of receiving the voice information over a telephone line.

26. An apparatus for processing a voice message, comprising:

means for storing one or more voice representations, wherein each voice representation corresponds to a word or phrase and is associated with a value, and for storing one or more actions;

means for receiving a voice message;

means for receiving a one of;

a user-specified word and a user-specified phrase from a user, the received user-specified word or phrase corresponding to a word or phrase having a corresponding stored voice representation; and

means for analyzing the voice message to determine if one or more of the stored voice representations corresponding to the received user-specified word or phrase occur in the voice message and to generate a final criteria measurement value associated with the voice message, and performing one or more of the stored actions based on the final criteria measurement value, if one or more of the stored voice representations are found to occur in the voice message, the final criteria measurement value based on the value associated with each determined stored voice representation occurring in the voice message.

27. An apparatus for analyzing voice information received from a person over a communications line, comprising:

means for storing one or more voice representations, where each voice representation corresponds to a word or phrase and is associated with a value, and for storing one or more actions;

means for receiving voice information from a person over a communications line;

means for receiving a one of;

a user-specified word and a user-specified phrase from a user, the received user-specified word or phrase corresponding to a word or phrase having a corresponding stored voice representation; and

means for analyzing the voice information from the person to determine if one or more of the stored voice representations corresponding to the received user-specified word or phrase occur in the voice information received from the person and to generate a final criteria measurement value associated with the voice information, and performing one or more of the stored actions based on the final criteria measurement value if the voice information is found to include one or more of the voice representations, the final criteria measurement value based on the value associated with each determined stored voice representation occurring in the voice information.

28. A non-transitory computer readable medium whose contents cause a computer to perform a procedure for processing a voice message comprising:

receiving a voice message;

receiving a one of;

a user-specified word and a user-specified phrase from a user, the received user-specified word or phrase corresponding to a word or phrase having a corresponding stored voice representation;

analyzing to voice message to determine if one or more stored voice representations corresponding to the received user-specified word or phrase occur in the voice message, wherein each voice representation corresponds to a word or phrase and is associated with a value, wherein analyzing the voice message comprises generating a final criteria measurement value associated with the voice message; and

performing one or more stored actions based on the final criteria measurement value if one or more of the stored voice representations are determined to occur in the voice message.

29. A non-transitory computer readable medium whose contents cause a computer to perform a procedure for processing voice information comprising:

receiving voice information from a person over a communications line;

receiving a one of;

a user-specified word and a user-specified phrase from a user, the received user-specified word or phrase corresponding to a word or phrase having a corresponding stored voice representation;

analyzing the voice information from the person to determine if one or more stored voice representations corresponding to the received user-specified word or phrase occur in the voice information, wherein each voice representation corresponds to a word or phrase and is associated with a value, wherein analyzing the voice information comprises generating a final criteria measurement value associated with the voice information; and

performing one or more stored actions based on the final criteria measurement value if one or more of the stored voice representations are determined to occur in the voice information.