System and method for handling missing speech data
View Patent ↗Disclosed herein are systems, computer-implemented methods, and tangible computer-readable media for handling missing speech data. The computer-implemented method includes receiving speech with a missing segment, generating a plurality of hypotheses for the missing segment, identifying a best hypothesis for the missing segment, and recognizing the received speech by inserting the identified best hypothesis for the missing segment. In another method embodiment, the final step is replaced with synthesizing the received speech by inserting the identified best hypothesis for the missing segment. In one aspect, the method further includes identifying a duration for the missing segment and generating the plurality of hypotheses of the identified duration for the missing segment. The step of identifying the best hypothesis for the missing segment can be based on speech context, a pronouncing lexicon, and/or a language model. Each hypothesis can have an identical acoustic score.
1. A method comprising:
receiving speech with a missing segment;
generating, via a processor, a plurality of hypotheses for the missing segment based at least in part on an acoustic feature of the received speech;
generating possible options for the missing segment, each possible option comprising the speech and a hypothesis of the plurality of hypotheses at a location of the missing segment;
assigning a same acoustic score to each hypothesis of the plurality of hypotheses; and
evaluating the possible options using the same acoustic score to identify a possible option that represents the speech.
2. The method of claim 1 , the method further comprising:
identifying a duration for the missing segment; and
generating the plurality of hypotheses having a length equal to the duration.
3. The method of claim 1 , wherein evaluating the possible options is based on speech context.
4. The method of claim 1 , wherein evaluating the possible options is based on a pronouncing lexicon.
5. The method of claim 1 , wherein evaluating the possible options is based on a language model.
6. The method of claim 1 , wherein the same acoustic score reflects a certainty of the plurality of hypotheses.
7. A computer-readable storage device storing instructions which, when executed by a computing device, cause the computing device to perform operations comprising:
receiving speech with a missing segment;
generating a plurality of hypotheses for the missing segment based at least in part on an acoustic feature of the received speech;
generating possible options for the missing segment, each possible option comprising the speech and a hypothesis of the plurality of hypotheses at a location of the missing segment;
assigning a same acoustic score to each hypothesis of the plurality of hypotheses; and
evaluating the possible options using the same acoustic score to identify a possible option that represents the speech.
8. The computer-readable storage device of claim 7 , the steps further comprising:
identifying a duration for the missing segment; and
generating the plurality of hypotheses having a length equal to the duration.
9. The computer-readable storage device of claim 7 , wherein evaluating the possible options is based on speech context.
10. The computer-readable storage device of claim 7 , wherein evaluating the possible options is based on a pronouncing lexicon.
11. The computer-readable storage device of claim 7 , wherein evaluating the possible options is based on a language model.
12. The computer-readable storage device of claim 7 , wherein the identical acoustic score reflects a certainty of the plurality of hypotheses.
13. A system comprising:
a processor; and
a computer-readable storage device storing instructions which, when executed on the processor, perform a method comprising:
receiving speech with a missing segment;
generating a plurality of hypotheses for the missing segment based at least in part on an acoustic feature of the received speech;
generating possible options for the missing segment, each possible option comprising the speech and a hypothesis of the plurality of hypotheses at a location of the missing segment;
assigning a same acoustic score to each hypothesis of the plurality of hypotheses; and
evaluating the possible options using the same acoustic score to identify a possible option that represents the speech.
14. The system of claim 13 , the computer-readable storage device stores further instructions, which, when executed by the processor, cause the processor to perform further operations comprising:
identifying a duration for the missing segment; and
generating the plurality of hypotheses having a length equal to the duration.
15. The system of claim 13 , wherein evaluating the possible options is based on speech context.
16. The system of claim 13 , wherein evaluating the possible options is based on a pronouncing lexicon.
17. The system of claim 13 , wherein evaluating the possible options is based on a language model.
18. The system of claim 13 , wherein the same acoustic score reflects a certainty of the plurality of hypotheses.