Method and system for providing captioned telephone service with automated speech recognition

1. A method for providing captioned telephone service, the method comprising:

initiating a first captioned telephone service call;

during the first captioned telephone service call, creating a first set of captions using a human captioner;

simultaneous with creating the first set of captions using a human captioner, creating a second set of captions using an automated speech recognition captioner;

comparing the first set of captions and the second set of captions using a scoring algorithm;

in response to the score of second set of captions being within predetermined range of scores, continuing the call using only the automated speech recognition captioner; and

in response to the score of second set of captions being outside of a predetermined range of scores, continuing the call using a human captioner.

2. The method of claim 1 , further comprising storing performance statistics associated with the first captioned telephone service call in a database.

3. The method of claim 2 , further comprising determining a probability of success of automated speech recognition captioning based on the stored performance statistics.

4. The method of claim 3 , further comprising:

initiating a second captioned telephone service call;

routing the second captioned telephone service call to a human captioner if the probability of success of automated speech recognition is below a predetermined threshold for the call; and

routing the second captioned telephone service call to an automated speech recognition captioner if the probability of success of automated speech recognition is above a predetermined threshold for the call.

5. The method of claim 4 , in which the predetermined threshold is determined by a service level agreement.

6. The method of claim 1 , in which the first captioned telephone service call is an internet protocol captioned telephone service (IP-CTS) call.

7. The method of claim 1 , in which comparing the first set of captions and the second set of captions is performed substantially in real time during the first captioned telephone service call.

8. The method of claim 1 , further comprising:

storing data indicating whether the human captioner or the automated speech recognition captioner was used to complete the first call;

initiating a second captioned telephone service call;

retrieving the data indicating whether the human captioner or the automated speech recognition captioner was used to complete the first call; and

using, on the second captioned telephone service call, the human captioner or the automated speech recognition captioner based on the stored data.

9. The method of claim 1 , further comprising:

storing data indicating one or more performance statistics of the first call;

initiating a second captioned telephone service call;

retrieving the data indicating one or more performance statistics of the first call; and

using, on the second captioned telephone service call, the human captioner or the automated speech recognition captioner based on the stored data.

10. The method of claim 9 , in which the data indicating one or more performance statistics of the first call includes a percent word match between the ASR captioner and the human captioner.

11. The method of claim 9 , in which the data indicating one or more performance statistics of the first call includes an average number of words not matched per minute of call audio.

12. The method of claim 9 , in which the data indicating one or more performance statistics of the first call includes a number of words per minute of call duration.

13. The method of claim 9 , in which the data indicating one or more performance statistics of the first call includes a percent of time speaking versus dead air time on the first call.

14. A method for providing captioned telephone service, the method comprising:

initiating a first captioned telephone service call;

creating, using an automated speech recognition captioner, captions based on words spoken by a first party to the first captioned telephone service call;

displaying the captions to a second party to the first captioned telephone service call;

measuring the accuracy of the captions with respect to the words spoken by the first party;

in response to the accuracy of the captions being within predetermined accuracy range, continuing to create captions using automated speech recognition; and

in response to the accuracy of the captions being outside of a predetermined accuracy range, creating captions for the remainder of the captioned telephone service call using a human captioner.

15. The method of claim 14 , in which measuring the accuracy of the captions with respect to the words spoken by the first party further comprises:

prompting the first party to speak a predetermined set of words; and

measuring the accuracy of the captions with respect to the predetermined set of words spoken by the first party.

16. The method of claim 14 , in which the automated speech recognition captioner is selected from a plurality of automated speech recognition captioners; and

in which the measured accuracy of the captions generated by the automated speech recognition captioner stored in a database record associated with the associated with the first captioned telephone service call.

17. The method of claim 16 , further comprising:

initiating a second captioned telephone service call;

selecting an automated speech recognition captioner for the second captioned telephone service call based on the accuracy

creating, using the selected automated speech recognition captioner, captions based on words spoken by a first party to the captioned telephone service call;

displaying the captions to a second party to the second captioned telephone service call.

18. A method for providing captioned telephone service, the method comprising:

initiating a first captioned telephone service call;

during the first captioned telephone service call, creating a first set of captions using a human captioner;

simultaneous with creating the first set of captions using a human captioner, creating a second set of captions using an automated speech recognition captioner;

comparing the first set of captions and the second set of captions using a scoring algorithm;

determining whether the first set of captions is outside of a predetermined range of scores; and

in response to the score of first set of captions being outside of a predetermined range of scores, setting an electronic flag indicative of the human captioner being in need of corrective action.

19. The method of claim 18 , further comprising transmitting an electronic communication to a person responsible for initiating the corrective action.

20. The method of claim 18 , in which the corrective action comprises providing additional training to the human captioner.