Granted Patent B2

US 7,356,134 · App. 11/004,287 · Granted Apr 8, 2008

Abstract

Claims (83)

1. A method of accessing a service, comprising:

receiving a speech signal to form a first utterance;

recognizing the first utterance using speaker independent speaker recognition;

determining if a user has not used the service previously;

when the user has not used the service previously, requesting the user to enter a personal identification number; and

when the personal identification number is valid:

requesting the user to speak to form a second utterance;

when the first utterance and the second utterance are sufficiently similar,

generating a reference utterance based on the first utterance and the second utterance; and

providing access to the service.

2. The method of claims 1 , further comprising

when the user has used the service previously, verifying the user based on the first utterance using a speaker verification system.

3. The method of claim 2 , further including:

when the user cannot be verified, requesting the user enter the personal identification number; and

when the personal identification number is valid, providing access to the service.

4. The method of claim 2 , wherein verifying the user based on the first utterance comprises

determining that the user is a male, when a preselected digit of at least one of the first utterance or the second utterance is detected.

5. The method of claim 4 , further comprising

determining a similarity between another utterance and the reference utterance using a male variance vector.

6. The method of claim 5 , further comprising

calculating a weighted Euclidean distance between the other utterance and the reference utterance.

7. The method of claim 4 , further comprising

determining that the user is a female, when the preselected digit is not detected;

determining a similarity between another utterance and the reference utterance using a female variance vector when calculating a weighted Euclidean distance between the other utterance and the reference utterance.

8. The method of claim 1 , wherein

the reference utterance is a generalization utterance of the first utterance and the second utterance.

9. The method of claim 1 , further comprising:

determining a similarity between the first utterance and the second utterance; and

storing the reference utterance when the similarity meets a threshold.

10. The method of claim 9 , further comprising:

when the similarity does not meet the threshold, requesting the user speakto form a third utterance;

determining a similarity between the first utterance and the third utterance;

when the similarity meets the threshold, generating another reference utterance based on the first utterance and the third utterance and storing the other reference utterance.

11. The method of claim 1 , wherein the speech signal, the first utterance, and the second utterance are representative of a plurality of digits, and wherein recognizing the first utterance using speaker independent speaker recognition comprises recognizing the plurality of digits using speaker independent speaker recognition.

12. The method of claim 1 , wherein the service is a dial-up service.

13. The method of claim 1 , further comprising connecting to the user in response to the user having initiated communication with the service.

14. A method of providing access to a service, comprising:

requesting an access code be spoken, to form a first plurality of utterances;

recognizing the access code using a speaker independent voice recognition process;

when a user has not previously utilized the service, requesting the user speak the access code a second time to form a second plurality of utterances;

determining a similarity between the first plurality of utterances and the second plurality of utterances; and

when the similarity meets a threshold, storing a reference plurality of utterances based on the first plurality of utterances and the second plurality of utterances.

15. The method of claim 14 , further comprising

allowing the user access to the service.

16. The method of claim 14 , further comprising

when the similarity does not meet the threshold, allowing the user access to the service.

17. The method of claim 14 , further comprising:

when the similarity does not meet the threshold, requesting the user to speak the access code to form a third plurality of utterances;

determining a similarity between the first plurality of utterances and the third plurality of utterances; and

when the similarity meets a threshold, storing a reference plurality of utterances based on the first plurality of utterances and the third plurality of utterances.

18. The method of claim 17 , further comprising

allowing the user access to the service.

19. The method of claim 17 , further comprising

when the similarity does not meet the threshold, allowing the user access to the service.

20. The method of claim 14 , further comprising

when the user has used the service previously, verifying the user based on the first plurality of utterances using a speaker verification system.

21. The method of claim 20 , further comprising

when the user is verified, allowing the user access to the service.

22. The method of claim 20 , further comprising:

when the user is not verified, requesting the user to speak the access code to form a third plurality of utterances;

verifying the user based on the third plurality of utterances using a speaker verification system;

when the user cannot be verified based on the third plurality of utterances, and the first plurality of utterances form a valid access code, allowing the user access to the service.

23. The method of claim 14 , further comprising:

when the user subsequently enters the number of the service, requesting the access code be spoken to form a third plurality of utterances;

verifying the user based on a similarity between the third plurality of utterances and the plurality of reference utterances using a speaker verification system.

24. The method of claim 14 , further comprising connecting via the service to the user.

25. The method of claim 14 , wherein the access code includes a plurality of numbers, and wherein recognizing the first utterance comprises recognizing the plurality of numbers.

26. The method of claim 14 , wherein the service is a dial-up service.

27. A method of accessing a service, comprising:

receiving a speech signal to form a first utterance;

recognizing the first utterance using speaker independent speaker recognition;

determining whether the user is verified based on the first utterance using a speaker verification system that has only two possible decisions;

requesting the user to speak to form a second utterance:

requesting the user to enter a personal identification number; and

when the personal identification number is valid, providing the user access to the service based on the first utterance, the second utterance, and the valid personal identification number.

28. The method of claim 27 , wherein the two possible decisions of the speaker verification decision are verified and not verified.

29. The method of claim 27 , wherein requesting the user to enter the personal identification number comprises requesting the user to enter the personal identification number in response to determining that the user is not verified.

30. The method of claim 27 , wherein determining whether the user is verified comprises determining whether the user is verified in response to determining that the user has previously accessed the service.

31. The method of claim 27 , further comprising receiving the personal identification number in response to the user speaking the personal identification number.

32. The method of claim 27 , further comprising when the first utterance and the second utterance are sufficiently similar, generating a reference utterance based on the first utterance and the second utterance.

33. The method of claim 27 , wherein providing the user access to the service based on the first utterance comprises providing the user access to the service based on recognizing the first utterance.

34. The method of claim 27 , wherein the speech signal and the first utterance are representative of a plurality of digits, and wherein recognizing the first utterance using speaker independent speaker recognition comprises recognizing the plurality of digits using speaker independent speaker recognition.

35. The method of claim 27 , wherein the service is a dial-up service.

Assignments (8)