Method and system of providing interactive speech recognition based on call routing

1. A method comprising:

applying a voice utterance, received in a telephone call, to speech recognition processing for correlation with one of a plurality of stored phrases respectively representing a plurality of destinations;

directing the call to a first one of the plurality of destinations correlated with the utterance by the speech recognition processing;

determining that the call was thereafter directed to a second one of the plurality of destinations; and

mapping the utterance to the second destination in response to the determining step.

2. A method as recited in claim 1 , further comprising:

determining that the call has not been redirected to a third destination prior to the mapping step.

3. A method as recited in claim 2 , further comprising:

repeating the mapping step for a plurality of telephone calls;

accumulating results of the mapping step for the plurality of telephone calls; and

adjusting an acoustic model in accordance with the accumulated results.

4. A method as recited in claim 3 , wherein the acoustic model provides a confidence level for the speech recognition processing.

5. A method as recited in claim 1 , wherein the stored phrases represent interactive options.

6. A method comprising:

storing data records in a database, the records corresponding, respectively, to a plurality of telephone call destinations;

prompting a telephone caller for a voice input;

receiving an utterance from the caller in response to the prompting step;

applying speech recognition processing to the received utterance;

matching the utterance to one of the stored records in accordance with the speech recognition processing;

directing the telephone call to the destination corresponding to the matched record;

determining that the call thereafter has been directed to a second destination corresponding to another one of the stored records; and

mapping the utterance to the second destination.

7. A method as recited in claim 6 , further comprising:

determining that the call has not been redirected to a third destination prior to the mapping step.

8. A method as recited in claim 7 , further comprising:

repeating the mapping step for a plurality of telephone calls;

accumulating results of the mapping step for the plurality of telephone calls; and

adjusting an acoustic model in accordance with the accumulated results.

9. A method as recited in claim 8 , wherein the acoustic model provides a confidence level for the speech recognition processing.

10. A method as recited in claim 6 , wherein the stored phrases represent interactive options.

11. Apparatus comprising:

a grammar database configured to store a plurality of selected phrases corresponding, respectively, to a plurality of destinations to which a user may be directed;

speech recognition logic coupled to the grammar database and configured to match received audio input from the user to a destination corresponding a phrase stored in the grammar database;

an acoustic model database coupled to the speech recognition logic and configured to provide a level of confidence for matching by the speech recognition logic;

wherein, in response to redirection of the user from a first destination matched by the speech recognition logic to a second destination, the received audio input is mapped to the second destination.

12. Apparatus as recited in claim 11 , wherein the second destination corresponds to another one of the stored selected phrases.

13. Apparatus as recited in claim 11 , wherein the stored phrases represent interactive options.

14. Apparatus as recited in claim 11 , wherein the received audio input is mapped to the second destination only if the user has not been redirected to a third destination.

15. Apparatus as recited in claim 11 , wherein the speech recognition logic is configured to accumulate results of mapping of utterances received in a plurality of telephone calls.

16. Apparatus as recited in claim 15 , wherein the acoustic model database is adjusted in accordance with the accumulated mapping results.

17. A system comprising:

an interactive voice response unit configured to generate a prompt to a caller for a voice input of one of a plurality of designated phrases corresponding, respectively, to stored data records associated with respective call destinations;

speech recognition logic coupled to the interactive voice response unit and configured to receive audio input from the caller;

a grammar database coupled to the speech recognition logic, the grammar database comprising data representations of the designated phrases;

wherein an utterance from the caller, received in response to a prompt, is matched to one of the stored records for directing the call to the associated destination; and

if the call thereafter has been redirected to a second destination corresponding to another one of the stored records, the utterance is mapped to the second destination.

18. A system as recited in claim 17 , further comprising:

an acoustic model database coupled to the speech recognition logic and configured to provide a level of confidence for matching received user audio input, as processed by the speech recognition logic, with the plurality of stored phrases.

19. A system as recited in claim 17 , wherein the system is based at a telecommunication provider premises for providing subscriber service, and the prompt generated by the interactive voice response unit provides identified service options via telephone line communication to the user at a remote location.

20. A system as recited in claim 17 , wherein the acoustic model is adjusted in accordance with an accumulation of mapped utterances to second destinations.