System and method for enhancing speech recognition accuracy
View Patent ↗Disclosed herein are systems, computer-implemented methods, and computer-readable media for enhancing speech recognition accuracy. The method includes dividing a system dialog turn into segments based on timing of probable user responses, generating a weighted grammar for each segment, exclusively activating the weighted grammar generated for a current segment of the dialog turn during the current segment of the dialog turn, and recognizing user speech received during the current segment using the activated weighted grammar generated for the current segment. The method can further include assigning probability to the weighted grammar based on historical user responses and activating each weighted grammar is based on the assigned probability. Weighted grammars can be generated based on a user profile. A weighted grammar can be generated for two or more segments. Exclusively activating each weighted grammar can include a transition period blending the previously activated grammar and the grammar to be activated.
1. A method comprising:
identifying, via a processor, segments of a dialog system based on a timing of probable user responses;
exclusively activating a weighted grammar for a specific segment of dialog in the dialog system during the specific segment, to yield an activated weighted grammar; and
recognizing user speech received during the specific segment of the dialog using the activated weighted grammar.
2. The method of claim 1 , further comprising assigning a probability to the weighted grammar based on historical user responses and activating the weighted grammar based on the probability.
3. The method of claim 1 , further comprising weighting a grammar based on an expected probable user response.
4. The method of claim 1 , wherein exclusively activating the weighted grammar further comprises a initiating a transition period blending a previously activated grammar and the weighted grammar to be activated.
5. The method of claim 1 , wherein the weighted grammar is weighted based on a user profile.
6. The method of claim 1 , wherein two identified segments are associated with the weighted grammar.
7. The method of claim 1 , further comprising presenting a menu to a user using the dialog turn system prior to receiving the user speech.
8. A system comprising:
a processor; and
a computer-readable storage medium storing having instructions stored which, when executed on the processor, cause the processor to perform operations comprising:
identifying segments of a dialog system based on a timing of probable user responses;
exclusively activating a weighted grammar for a specific segment of dialog in the dialog system during the specific segment of the dialog turn, to yield an activated weighted grammar; and
recognizing user speech received during the specific segment of the dialog using the activated weighted grammar.
9. The system of claim 8 , the computer-readable storage medium having additional instructions stored which result in operations further comprising assigning a probability to the weighted grammar based on historical user responses and activating the weighted grammar based on the probability.
10. The system of claim 8 , the computer-readable storage medium having additional instructions stored which result in operations further comprising weighting a grammar based on an expected probable user response.
11. The system of claim 8 , wherein exclusively activating the weighted grammar further comprises a initiating a transition period blending a previously activated grammar and the weighted grammar to be activated.
12. The system of claim 8 , wherein the weighted grammar is weighted based on a user profile.
13. The system of claim 8 , wherein two identified segments are associated with the weighted grammar.
14. The system of claim 8 , the computer-readable storage medium having additional instructions stored which result in operations further comprising presenting a menu to a user using the dialog turn system prior to receiving the user speech.
15. A computer-readable storage device having instructions stored which, when executed on a computing device, cause the computing device to perform operations comprising:
identifying segments of a dialog system based on a timing of probable user responses;
exclusively activating a weighted grammar for a specific segment of dialog in the dialog system during the specific segment of the dialog, to yield an activated weighted grammar; and
recognizing user speech received during the specific segment using the activated weighted grammar.
16. The computer-readable storage device of claim 15 , having additional instructions stored which result in operations further comprising assigning a probability to the weighted grammar based on historical user responses and activating the weighted grammar based on the probability.
17. The computer-readable storage device of claim 15 , having additional instructions stored which result in operations further comprising weighting a grammar based on an expected probable user response.
18. The computer-readable storage device of claim 15 , wherein exclusively activating the weighted grammar further comprises a initiating a transition period blending a previously activated grammar and the weighted grammar to be activated.
19. The computer-readable storage device of claim 15 , wherein the weighted grammar is weighted based on a user profile.
20. The computer-readable storage device of claim 15 , wherein two identified segments are associated with the weighted grammar.