Voice recognition of telephone conversations

• US 6,278,772 B1
• Filed: 06/30/1998
• Issued: 08/21/2001
• Est. Priority Date: 07/09/1997
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bowater, Ronald John, Porter, Lawrence Leon
• Primary Examiner(s): Tsang, Fan
• Assistant Examiner(s): Escalante, Ovidio
• Application Number:
  US09/107,686
• Time in Patent Office: 1,148 Days
• Field of Search: 379/265, 379/88.16, 379/34, 379/35, 379/202, 379/88.13, 379/280, 379/258-267, 379/203, 379/201, 379/67.1, 379/68
• US Class Current: 379/88.13
• CPC Class Codes: H04M 2201/60 Medium conversion
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656

Abstract

Voice data requires large storage resources even when compressed and takes a long time to retrieve. Further the required information cannot normally be directly located and it is difficult to analyze the voice data for statistical information. There is described a method for performing a voice recognition function on a voice telephone conversation to convert the conversation into text data using a voice processing system. The method comprises receiving voice data representing the telephone conversation comprising a first series of speech data from an agent interspersed with a second series of speech data from a client and storing the first and second series of speech data as a single body of voice data for later retrieval. Then a voice recognition function is performed on the voice data to convert it into text data representing the telephone conversation and the text data is stored for later retrieval. Such a solution allows entire days/weeks or even months of conversation to be stored and accessed. Since the memory space required is considerably smaller for text storage it is possible to keep many days of conversation in directly accessible memory that may be searched by a computer. Furthermore it is possible to search for keywords typed from the keyboard and it is not necessary to manually scan the entire conversation for the desired topic.

Claims

1. In a voice processing system having a voice recognition resource for processing voice data, a method for processing a telephone conversation comprising the steps of:

receiving voice data representing the telephone conversation comprising a first series of speech data from an agent workstation interspersed with a second series of speech data from a client workstation;

storing the first and second series of speech data for later retrieval by the voice processing system for voice recognition processing;

monitoring the capacity of the voice recognition resource;

determining if there is enough capacity in the voice recognition resource; and

when so determined performing voice recognition on the voice data to convert it into text data representing the telephone conversation; and

storing the text data for later retrieval.

2. A method as claimed in claim 1 further comprising the steps of:

receiving the first series of speech data from the agent and second series of speech data from the client as a single sequence of voice data.

3. A method as claimed in claim 2 further comprising said voice processing system 8 being a third party in a conference call between said agent and said client.

4. A method as claimed in claim 1 further comprising the steps of:

receiving the first series of speech data from the agent and sending it on to the client; and

receiving the second series of speech data from the client and sending it on to the agent.

5. A method as claimed in claim 4 further comprising combining the first and second series of speech data to form a single sequence of voice data.

6. A method as claimed in claim 5 wherein the voice recognition function is performed in slower than real time.

7. A method as claimed in claim 6 wherein the voice data for a plurality of conversations is stored together and converted together.

8. A method as claimed in claim 7 wherein the voice and text data are stored together.

9. A method as claimed in claim 4 further comprising the step of storing an identifier associated with each message indicating the originator of the message and/or indicating the start time of the message.

10. A method as claimed in claim 9 comprising storing the identifiers in a control file associated with the conversation.

11. A method as claimed in claim 10 further comprising the steps of:

receiving a search request including search criteria;

searching for the text data on the storage device comprising the search criteria; and

locating the text data and corresponding voice data according to the search criteria.

12. A voice processing system comprising:

a voice recognition resource for processing voice data

means for receiving voice data representing the telephone conversation comprising a first series of speech data from an agent interspersed with a second series of speech data from a client;

means for storing the first and second series of speech data as a single body of voice data for later retrieval;

means for monitoring the usage of the voice recognition resource;

means for determining if there is enough resource capacity in the voice processing system; and

means for, when so determined, initiating voice recognition on the voice data to convert them into text data representing the telephone conversation; and

means for storing the text data for later retrieval.

13. A voice processing system as claimed in claim 12 further comprising:

means for receiving the first series of speech data from the agent and second series of speech data from the client as a single sequence of voice data.

14. A voice processing system as claimed in claim 13 whereby said voice processing system (8) is a third party in a conference call between said agent and said client.

15. A voice processing system as claimed in claim 12 further comprising:

means for receiving the first series of speech data from the agent and sending it on to the client; and

means for receiving the second series of speech data from the client and sending it on to the agent.

16. A voice processing system as claimed in claim 15 further comprising:

means for combining the first and second series of speech data to form a single sequence of voice data.

17. A voice processing system as claimed in claim 16 wherein the voice recognition function is performed in slower than real time.

18. A voice processing system as claimed in claim 17 wherein the voice data for a plurality of conversations is stored together and converted together.

19. A voice processing system as claimed in claim 18 wherein the voice and text data are stored together.

20. A voice processing system as claimed in claim 15 further comprising:

means for storing an identifier associated with each message indicating the originator of the message and/or indicating the start time of the message.

21. A voice processing system as claimed in claim 20 comprising:

means for storing the identifiers in a control file associated with the conversation.

22. A method as claimed in claim 21 further comprising:

means for receiving a search request including search criteria;

means for searching for the text data on the storage device comprising the search criteria; and

means for locating the text data and corresponding voice data according to the search criteria.

23. A computer-readable storage medium storing a computer program product that, when run in a voice processing system comprising a voice recognition resource for processing voice data, the stored program executing the steps of:

receiving voice data representing the telephone conversation comprising a first series of speech data from an agent workstation interspersed with a second series of speech data from a client workstation;

storing the first and second series of speech data for later retrieval by the voice processing system for voice recognition processing;

monitoring the capacity of the voice recognition resource;

determining if there is enough capacity in the voice recognition resource; and

when so determined, performing voice recognition on the voice data to convert it into text data representing the telephone conversation; and

storing the text data for later retrieval.

24. A computer-readable storage medium as claimed in claim 23 wherein said stored program further executing the steps of:

receiving the first series of speech data from the agent and second series of speech data from the client as a single sequence of voice data.

25. A computer-readable storage medium as in claim 24 wherein said voice processing system being a third party in a conference call between said agent and said client.

26. A computer-readable storage medium as in claim 24 said stored program further executing the steps of:

receiving the first series of speech data from the agent and sending it on to the client; and

receiving the second series of speech data from the client and sending it on to the agent.

27. A computer-readable storage medium as in claim 26 said stored program further executing the step of combining the first and second series of speech data to form a single sequence of voice data.

28. A computer-readable storage medium as claimed in claim 27 wherein the voice recognition function is performed in slower than real time.

29. A computer-readable storage medium as in claim 28 wherein the voice data for a plurality of conversations is stored together and converted together.

30. A computer-readable storage medium as in claim 29 wherein the voice and text data are stored together.

31. A computer-readable storage medium as in claim 26 wherein the stored program further executing the step of storing an identifier associated with each message indicating the originator of the message and/or indicating the start time of the message.

32. A computer-readable storage medium as in claim 31 wherein the stored program further executing the step of storing the identifiers in a control file associated with the conversation.