System and method for enhancing speech recognition accuracy
View Patent ↗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 computer-implemented method of enhancing speech recognition accuracy, the method comprising:
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 respective segment of the dialog turn during the respective segment of the dialog turn; and
recognizing user speech received during the respective segment using the activated weighted grammar generated for the respective segment.
2. The computer-implemented method of claim 1 , the method further comprising assigning probability to the weighted grammar based on historical user responses and activating the weighted grammar based on the assigned probability.
3. The computer-implemented method of claim 1 , wherein weighted grammars are based on a user profile.
4. The computer-implemented method of claim 1 , wherein the weighted grammar is generated for two or more contiguous segments.
5. The computer-implemented method of claim 1 , wherein exclusively activating each weighted grammar further includes a transition period blending the previously activated grammar and the grammar to be activated.
6. The computer-implemented method of claim 1 , wherein the weighted grammar is based on one or more expected probable user response.
7. The computer-implemented method of claim 1 , the method further comprising:
dynamically generating a menu in a natural language dialog based on an event;
presenting the dynamically generated menu to a user during a system dialog turn; and
generating a weighted grammar for each segment based on the dynamically generated menu.