SYSTEM AND METHOD FOR HANDLING MISSING SPEECH DATA

摘要

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.

主权项

1. A method comprising:
receiving, by a system comprising a processor, speech data; detecting, by the system, a missing segment in the speech data resulting from an interruption occurring in a communication network conveying the speech data; generating, by the system, a plurality of hypothetical segments for the missing segment; determining, by the system, a duration of the missing segment; and evaluating, by the system, the plurality of hypothetical segments according to a context of speech determined from the speech data and the duration of the missing segment to identify a possible segment that represents the missing segment of the speech data.