Method of and system for improving accuracy in a speech recognition system

• US 8,812,314 B2
• Filed: 11/12/2009
• Issued: 08/19/2014
• Est. Priority Date: 07/31/2000
• Status: Expired due to Fees

• Current Assignee: Eliza Corporation (Gainwell Technologies)
• Original Assignee: Eliza Corporation (Gainwell Technologies)
• Inventors: Kroeker, John, Boulanov, Oleg
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US12/616,874
• Publication Number:
  US 20100100378A1
• Time in Patent Office: 1,741 Days
• Field of Search: 704/235, 704/260, 704/257, 704/270, 704/275, 379/88.01
• US Class Current: 704/235
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A method for transcribing an audio response includes: A. constructing an application including a plurality of queries and a set of expected responses for each query, the set including a plurality of expected responses to each query in a textual form; B. posing each of the queries to a respondent with a querying device; C. receiving an audio response to each query from the respondent; D. performing a speech recognition function on each audio response with an automatic speech recognition device to transcribe each audio response to a textual response to each query; E. recording each audio response with a recording device; and F. comparing, with the automatic speech recognition device, each textual response to the set of expected responses for each corresponding query to determine if each textual response corresponds to any of the expected responses in the set of expected responses for the corresponding query.

Claims

1. A speech recognition system comprising:

a querying device for posing at least one query to a respondent;

a speech recognition device including a speak recognition application which receives an audio response from said respondent and transcribes said audio response to produce a corresponding text response, wherein the speech recognition device is operative to conduct a speaker-independent speech recognition analysis of said audio response, wherein the speech recognition device comprises means for processing of an acoustic file that is tied to database information resulting from the speech recognition application that audibly plays the acoustic file while presenting a screen to a transcriber for transcription and correction of the database information;

a storage device for storing said audio response as it is received by said speech recognition device; and

an accuracy determination device operative to compare said text response to a text set of expected responses and to determine whether said text response corresponds to one of said expected responses, wherein said accuracy determination device is operative to determine whether said text response does correspond to one of said expected responses within a predetermined accuracy confidence parameter, and flag said audio response for further review if said response does not correspond to one of said expected responses within the predetermined accuracy confidence parameter.

2. The speech recognition system of claim 1 further comprising a human interface device for enabling a human operator to view said at least one query and to hear said audio response that corresponds to said at least one query.

3. The speech recognition system of claim 2 wherein said human interface device comprises a personal computer including a monitor for enabling the operator to view said at least one query and an audio speaker device for enabling the operator to listen to said audio response.

4. The speech recognition system of claim 2 wherein said querying device includes a program having an application file, said application file including code which causes the at least one query to be posed to the respondent, a list of expected responses and an address at which a file containing the received audio response will be stored in the storage device.

5. The speech recognition system of claim 3 wherein said querying device includes a program having an application file, said application file including code which causes the at least one query to be posed to the respondent, a list of expected responses and an address at which a file containing the received audio response will be stored in the storage device.

6. The speech recognition system of claim 2 wherein said human interface device includes a graphical user interface on which the operator views said at least one query and said text set of expected responses wherein, after listening to said audio response, the operator is able to select one of said expected responses from said text set of expected responses.

7. The speech recognition system of claim 5 wherein said human interface device includes a graphical user interface on which the operator views said at least one query and said text set of expected responses wherein, after listening to said audio response, the operator is able to select one of said expected responses from said text set of expected responses.

8. The speech recognition system of claim 5 wherein said graphical user interface comprises an application navigation window for enabling the operator to navigate through said at least one query, and an audio navigation window for enabling the operator to control playback of said audio response.

9. The speech recognition system of claim 7 wherein said graphical user interface comprises an application navigation window for enabling the operator to navigate through said at least one query, and an audio navigation window for enabling the operator to control playback of said audio response.

10. The speech recognition system of claim 5 wherein said graphical user interface includes a text entry window which enables the operator to enter a text response if none of said expected responses from said text set of expected responses corresponds to said audio response.

11. The speech recognition system of claim 9 wherein said graphical user interface includes a text entry window which enables the operator to enter a text response if none of said expected responses from said text set of expected responses corresponds to said audio response.

12. A speech recognition system comprising:

a querying device for posing at least one query to a respondent;

a speech recognition device including a speech recognition application which receives an audio response from said respondent and transcribes said audio response to produce a corresponding text response, wherein the speech recognition device is operative to conduct a speaker-independent speech recognition analysis of said audio response, wherein the speech recognition device comprises means for processing of an acoustic file that is tied to database information resulting from the speech recognition application that audibly plays the acoustic file while presenting a screen to a transcriber for transcription and correction of the database information;

a storage device for storing said audio response as it is received by said speech recognition device; and

an accuracy determination device for comparing said text response to a text set of expected responses and determining whether said text response corresponds to one of said expected responses;

wherein, if said accuracy determination device determines that said text response does not correspond to one of said expected responses within a predetermined accuracy confidence parameter, said accuracy determination device flags said audio response for further review by a user.

13. The speech recognition system of claim 12 further comprising a human interface device for enabling a human operator to view said at least one query and to hear said audio response that corresponds to said at least one query.

14. The speech recognition system of claim 13 wherein said human interface device comprises a personal computer including a monitor for enabling the operator to view said at least one query and an audio speaker device for enabling the operator to listen to said audio response.

15. The speech recognition system of claim 13 wherein said querying device includes a program having an application file, said application file including code which causes the at least one query to be posed to the respondent, a list of expected responses and an address at which a file containing the received audio response will be stored in the storage device.

16. The speech recognition system of claim 14 wherein said querying device includes a program having an application file, said application file including code which causes the at least one query to be posed to the respondent, a list of expected responses and an address at which a file containing the received audio response will be stored in the storage device.

17. The speech recognition system of claim 13 wherein said human interface device includes a graphical user interface on which the operator views said at least one query and said text set of expected responses wherein, after listening to said audio response, the operator is able to select one of said expected responses from said text set of expected responses.

18. The speech recognition system of claim 16 wherein said human interface device includes a graphical user interface on which the operator views said at least one query and said text set of expected responses wherein, after listening to said audio response, the operator is able to select one of said expected responses from said text set of expected responses.

19. The speech recognition system of claim 16 wherein said graphical user interface comprises an application navigation window for enabling the operator to navigate through said at least one query, and an audio navigation window for enabling the operator to control playback of said audio response.

20. The speech recognition system of claim 18 wherein said graphical user interface comprises an application navigation window for enabling the operator to navigate through said at least one query, and an audio navigation window for enabling the operator to control playback of said audio response.

21. The speech recognition system of claim 16 wherein said graphical user interface includes a text entry window which enables the operator to enter a text response if none of said expected responses from said text set of expected responses corresponds to said audio response.

22. The speech recognition system of claim 20 wherein said graphical user interface includes a text entry window which enables the operator to enter a text response if none of said expected responses from said text set of expected responses corresponds to said audio response.

23. A method for transcribing an audio response by using a speech recognition device comprising means for processing of an acoustic file that is tied to database information resulting from a speech recognition application that audibly plays the acoustic file while presenting a screen to a transcriber for transcription and correction of the database information, the method comprising:

A. posing a query to a respondent;

B. receiving an audio response from said respondent;

C. performing a speaker-independent speech recognition analysis on said audio response to transcribe said audio response to a textual response;

D. recording said audio response;

E. comparing said textual response to a set of expected responses to said query, said set including a plurality of expected responses to said query in a textual form; and

F. flagging said audio response for further review by a user, if the corresponding textual response does not correspond to one of said expected responses in said set of expected responses.

24. The method of claim 23 further comprising;

G. listening to said audio response; and

H. selecting, from said set of expected responses, a textual response that corresponds to said audio response.

25. The method of claim 23 further comprising:

G. listening to said audio response; and

H. manually transcribing a textual response that corresponds to said audio response.

26. A method for transcribing an audio response by using a speech recognition device comprising means for processing of an acoustic file that is tied to database information resulting from a speech recognition application that audibly plays the acoustic file while presenting a screen to a transcriber for transcription and correction of the database information, the method comprising:

A. constructing a speaker-independent speech recognition application including a plurality of queries and a set of expected responses for each query, said set including a plurality of expected responses to each query in a textual form;

B. posing each of said queries to a respondent;

C. receiving an audio response to each query from said respondent;

D. performing a speech recognition function on each said audio response to transcribe each said audio response to a textual response to each query;

E. recording each audio response;

F. comparing each textual response to said set of expected responses for each corresponding query to determine if each textual response corresponds to any of said expected responses in said set of expected responses for the corresponding query; and

G. for further review by a user, flagging each audio response corresponding to a textual response that does not correspond to one of said expected responses in said set of expected responses to the corresponding query.

27. The method of claim 26 further comprising:

H. reviewing each flagged audio response to determine if a corresponding expected response is included in said set of expected responses for the query associated with each audio response.

28. The method of claim 27 further comprising selecting, from an associated set of expected responses for each query, a response that corresponds to said flagged audio response.

29. The method of claim 27 further comprising manually transcribing a response that corresponds to each flagged audio response.

30. A method for transcribing an audio response by using a speech recognition device comprising means for processing of an acoustic file that is tied to database information resulting from a speech recognition application that audibly plays the acoustic file while presenting a screen to a transcriber for transcription and correction of the database information, the method comprising:

A. constructing a speaker-independent speech recognition application including a plurality of queries and a set of expected responses for each query, said set including a plurality of expected responses to each query in a textual form;

B. posing each of said queries to a respondent with a querying device;

C. receiving an audio response to each query from said respondent;

D. performing a speech recognition function on each said audio response with an automatic speech recognition device to transcribe each said audio response to a textual response to each query;

E. recording each audio response with a recording device;

F. comparing, with said automatic speech recognition device, each textual response to said set of expected responses for each corresponding query to determine if each textual response corresponds to any of said expected responses in said set of expected responses for the corresponding query; and

G. for further review by a user, flagging each audio response corresponding to a textual response that does not correspond to one of said expected responses in said set of expected responses to the corresponding query.

31. The method of claim 30 further comprising:

H. reviewing each flagged audio response with a human interface device to determine if a corresponding textual response is included in said set of expected responses for the query associated with each audio response.