Learning transcription errors in speech recognition tasks

Apparatus, comprising:

• a processor;
• computer memory holding computer program instructions executed by the processor for identification of a mistranscription generated by a speech recognition system, the computer program instructions comprising:
• program code, operative to provide a set of known utterance members for use by a speech recognition system, each utterance member consisting of a respective plural number of words;
• program code, operative to match a received utterance to a first utterance member within the set of known utterance members, the first utterance member being a closest matching utterance member having a first plural number of words, wherein fewer than the first plural number of words in the received utterance are matched to the first plural number of words in the first utterance member and the received utterance varies in a first particular manner as compared to a first word in a first slot in the first utterance member;
• program code, operative to send the received utterance to a mistranscription analyzer component;
• program code, operative to increment evidence, by the mistranscription analyzer, that the received utterance is evidence of a mistranscription, wherein the evidence is an occurrence of one of a substitution error, a deletion error or an insertion error at the first slot in the received utterance;
• and
• program code responsive to incremented evidence for the mistranscription exceeding a threshold, operative to treat a future received utterance containing the mistranscription as though the first word was recognized.

A computer program product in a non-transitory computer readable medium for use in a data processing system, the computer program product holding computer program instructions executed by the data processing system for identification of a mistranscription generated by a speech recognition system, the computer program instructions comprising:

• program code, operative to provide a set of known utterance members for use by a speech recognition system, each utterance member consisting of a respective plural number of words;
• program code, operative to match a received utterance to a first utterance member within the set of known utterance members, the first utterance member being a closest matching utterance member having a first plural number of words, wherein fewer than the first plural number of words in the received utterance are matched to the first plural number of words in the first utterance member and the received utterance varies in a first particular manner as compared to a first word in a first slot in the first utterance member;
• program code, operative to send the received utterance to a mistranscription analyzer component;
• program code, operative to increment evidence, by the mistranscription analyzer, that the received utterance is evidence of a mistranscription, wherein the evidence is an occurrence of one of a substitution error, a deletion error or an insertion error at the first slot in the received utterance;
• and
• program code responsive to incremented evidence for the mistranscription exceeding a threshold, operative to treat a future received utterance containing the mistranscription as though the first word was recognized.