Speech and signal digitization by using recognition metrics to select from multiple techniques

• US 7,016,835 B2
• Filed: 12/19/2002
• Issued: 03/21/2006
• Est. Priority Date: 10/29/1999
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Kanevsky, Dimitri, Olsen, Peder Andreas, Eide, Ellen Marie, Gopinath, Ramesh Ambat
• Primary Examiner(s): ARMSTRONG, ANGELA A
• Application Number:
  US10/323,549
• Publication Number:
  US 20030115053A1
• Time in Patent Office: 1,188 Days
• Field of Search: 704229-233, 704238-256, 704271-275, 704/235, 704/236, 704/270, 382/229, 345/156, 341/50, 356/406, 379/406.08, 379/388.04
• US Class Current: 704/231
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: G10L 17/26 Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices

Abstract

A characteristic-specific digitization method and apparatus are disclosed that reduces the error rate in converting input information into a computer-readable format. The input information is analyzed and subsets of the input information are classified according to whether the input information exhibits a specific physical parameter affecting recognition accuracy. If the input information exhibits the specific physical parameter affecting recognition accuracy, the characteristic-specific digitization system recognizes the input information using a characteristic-specific recognizer that demonstrates improved performance for the given physical parameter. If the input information does not exhibit the specific physical parameter affecting recognition accuracy, the characteristic-specific digitization system recognizes the input information using a general recognizer that performs well for typical input information. In one implementation, input speech having very low recognition accuracy as a result of a physical speech characteristic is automatically identified and recognized using a characteristic-specific speech recognizer.

Claims

1. A system for digitizing input information from a first information type to a digital format, comprising:

a memory that stores computer readable code; and

a processor operatively coupled to said memory, said processor configured to;

analyze said input information to determine if at least one of at least first and second characteristics is present, wherein said processor is further configured to;

recognize said input information with a plurality of prioritized recognition methods that exhibit varying degrees of improved recognition for a certain characteristic of the input information; and

determine whether a general recognizer or an intermediate recognizer produces a script closer to a reference output;

select output information recognized with a first recognition method if said analyzing step determines that said input information includes said first characteristic; and

select output information recognized with a second recognition method if said analyzing step determines that said input information includes said second characteristic.

2. A method for digitizing input information from a first information type to a digital format, said method comprising the steps of:

analyzing said input information to determine if at least one of at least first and second characteristics is present, wherein said analyzing step further comprises the steps of;

recognizing said input information with a plurality of prioritized recognition methods that exhibit varying degrees of improved recognition for a certain characteristic of the input information; and

determining whether a general recognizer or an intermediate recognizer produces a script closer to a reference output;

selecting output information recognized with a first recognition method if said analyzing step determines that said input information includes said first characteristic; and

selecting output information recognized with a second recognition method if said analyzing step determines that said input information includes said second characteristic.

3. The method of claim 2, wherein said reference output is produced by a characteristic-specific recognizer.

4. The method of claim 2, wherein said reference output is obtained using a voting method.

5. The method of claim 2, wherein said input information type is speech.

6. The method of claim 2, wherein said input information type is handwriting.

7. The method of claim 2, wherein said input information type is printed text.

8. The method of claim 2, wherein said input information type is pictures.

9. A method for digitizing input information from a first information type to a digital format, said method comprising the steps of:

identifying portions of said input information having a characteristic that impairs recognition accuracy with a plurality of prioritized recognition methods that exhibit varying degrees of improved recognition for said characteristic and determining whether a general recognizer or an intermediate recognizer produces a script closer to a reference output; and

recognizing said input information portions with a recognizer that exhibits improved performance for said characteristic.

10. A system for digitizing input information from a first information type to a digital format, comprising:

a memory that stores computer readable code; and

a processor operatively coupled to said memory, said processor configured to;

identify portions of said input information having a characteristic that impairs recognition accuracy with a plurality of prioritized recognition methods that exhibit varying degrees of improved recognition for said characteristic and determining whether a general recognizer or an intermediate recognizer produces a script closer to a reference script; and

recognize said input information portions with a recognizer that exhibits improved performance for said characteristic.

11. A method for transcribing speech, said method comprising the steps of:

analyzing a speech sample to determine if at least one of at least first and second types of speech is present, wherein said analyzing step further comprises the steps of;

recognizing said speech with a plurality of prioritized speech recognition methods that exhibit varying degrees of improved speech recognition for a certain characteristic of the input speech; and

determining whether a general speech recognizer or an intermediate speech recognizer produces a script closer to a reference script;

selecting speech recognized with a first speech recognition method if said analyzing step determines that said speech sample includes said first type of speech; and

selecting speech recognized with a second speech recognition method if said analyzing step determines that said speech sample includes said second type of speech.

12. The method of claim 11, further comprising the step of generating an index of said speech samples with said first type of speech and an index of said speech samples with said second type of speech.

13. The method of claim 12, wherein said index is obtained using a voting method.

14. The method of claim 11, wherein said first type of speech is fast rate speech and said second type of speech is normal rate speech.

15. The method of claim 11, wherein said first type of speech is speech with background noise and said second type of speech is speech without background noise.

16. A system for transcribing speech, comprising:

a memory that stores computer readable code; and

a processor operatively coupled to said memory, said processor configured to;

analyze a speech sample to determine if at least one of at least first and second types of speech is present, wherein said processor is further configured to;

recognize said speech with a plurality of prioritized speech recognition methods that exhibit varying degrees of improved speech recognition for a certain characteristic of the input speech; and

determine whether a general speech recognizer or an intermediate speech recognizer produces a script closer to a reference script;

select speech recognized with a first speech recognition method if said analyzing step determines that said speech sample includes said first type of speech; and

select speech recognized with a second speech recognition method if said analyzing step determines that said speech sample includes said second type of speech.

17. A method for transcribing speech, said method comprising the steps of:

identifying portions of said speech having a characteristic that impairs speech recognition accuracy with a plurality of prioritized speech recognition methods that exhibit varying degrees of improved speech recognition for a certain characteristic of the input speech and determining whether a general speech recognizer or an intermediate speech recognizer produces a script closer to a reference script; and

recognizing said identified speech portions with a speech recognizer that exhibits improved performance for said characteristic.

18. The method of claim 17, further comprising the step of generating an index of said speech having said characteristic that impairs speech recognition accuracy and an index of said speech not having said characteristic that impairs speech recognition accuracy.

19. The method of claim 17, wherein said characteristic that impairs speech recognition accuracy is speech with background noise.

20. The method of claim 17, wherein said characteristic that impairs speech recognition accuracy is a speech rate that is faster than a normal speech rate.

21. A system for transcribing speech, comprising:

a memory that stores computer readable code; and

a processor operatively coupled to said memory, said processor configured to;

identify portions of said speech having a characteristic that impairs speech recognition accuracy with a plurality of prioritized speech recognition methods that exhibit varying degrees of improved speech recognition for a certain characteristic of the input speech and determining whether a general speech recognizer or an intermediate speech recognizer produces a script closer to a reference script; and

recognize said identified speech portions with a speech recognizer that exhibits improved performance for said characteristic.

22. A method for transcribing speech, said method comprising the steps of:

recognizing a speech sample with at least three speech recognition methods that are prioritized according to performance for a given characteristic of input speech, at least one of said speech recognition methods producing a reference script;

comparing said recognized speech samples with said reference script to identify portions of said speech having a characteristic that impairs speech recognition accuracy; and

selecting speech portions recognized with a speech recognizer that exhibits improved performance for said characteristic relative to a general speech recognizer.

23. The method of claim 22, further comprising the step of generating an index of said speech having said characteristic that impairs speech recognition accuracy and an index of said speech not having said characteristic that impairs speech recognition accuracy.

24. The method of claim 22, wherein said characteristic that impairs speech recognition accuracy is a speech rate that is faster than a normal speech rate.

25. The method of claim 22, wherein said characteristic that impairs speech recognition accuracy is speech with background noise.

26. A system for transcribing speech, comprising:

a memory that stores computer readable code; and

a processor operatively coupled to said memory, said processor configured to;

recognize a speech sample with at least three speech recognition methods that are prioritized according to performance for a given characteristic of input speech, at least one of said speech recognition methods producing a reference script;

compare said recognized speech samples with said reference script to identify portions of said speech having a characteristic that impairs speech recognition accuracy; and

select speech portions recognized with a speech recognizer that exhibits improved performance for said characteristic relative to a general speech recognizer.

27. An article of manufacture for digitizing input information from a first information type to a digital format, comprising:

a step to analyze said input information to determine if at least one of at least first and second types of information is present, wherein said step to analyze further comprises the steps of;

a step to recognize said input information with a plurality of prioritized recognition methods that exhibit varying degrees of improved recognition for a certain characteristic of the input information; and

a step to determine whether a general recognizer or an intermediate recognizer produces a script closer to a reference output;

a step to select output information recognized with a first recognition method if said analyzing step determines that said input information includes said first characteristic; and

a step to select output information recognized with a second recognition method if said analyzing step determines that said input information includes said second characteristic.

28. An article of manufacture for digitizing input information from a first information type to a digital format, comprising:

a step to identify portions of said input information having a characteristic that impairs recognition accuracy with a plurality of prioritized recognition methods that exhibit varying degrees of improved recognition for said characteristic and determining whether a general recognizer or an intermediate recognizer produces a script closer to a reference script; and

a step to recognize said input information portions with a recognizer that exhibits improved performance for said characteristic.

29. An article of manufacture for transcribing speech, comprising:

a step to analyze a speech sample to determine if at least one of at least first and second types of speech is present, wherein said step to analyze further comprises the steps of;

a step to recognize said speech with a plurality of prioritized speech recognition methods that exhibit varying degrees of improved speech recognition for a certain characteristic of the input speech; and

a step to determine whether a general speech recognizer or an intermediate speech recognizer produces a script closer to a reference script;

a step to select speech recognized with a first speech recognition method if said analyzing step determines that said speech sample includes said first type of speech; and

a step to select speech recognized with a second speech recognition method if said analyzing step determines that said speech sample includes said second type of speech.

30. An article of manufacture for transcribing speech, comprising:

a step to identify portions of said speech having a characteristic that impairs speech recognition accuracy with a plurality of prioritized speech recognition methods that exhibit varying degrees of improved speech recognition for a certain characteristic of the input speech and determining whether a general speech recognizer or an intermediate speech recognizer produces a script closer to a reference script; and

a step to recognize said identified speech portions with a speech recognizer that exhibits improved performance for said characteristic.