Automatic speech recognition reporting
View Patent ↗A method, a computer readable medium and a system for reporting automatic speech recognition that comprises, collecting an utterance, analyzing the utterance, receiving a translation of the utterance, and determining a difference between the analyzed utterance and the translated utterance. An embodiment the disclosure includes updating the utterance analysis based upon the determined difference, correlating the analyzed utterance to the translated utterance and tracking determined difference by a translator. In another embodiment the disclose includes reporting, categorizing, sorting, and grouping the determined difference.
1. A computer implemented method for reporting automatic speech recognition, comprising:
collecting an utterance;
transcribing and analyzing the utterance;
determining whether the utterance transcription contains grammar that is statistically common;
determining whether the utterance transcription contains grammar that is statistically uncommon;
receiving a translation of the utterance;
determining at least one difference between the analyzed utterance and the translated utterance using a processor; and
sorting the at least one determined difference, wherein
the determining whether the utterance transcription contains grammar that is statistically common and the determining whether the utterance transcription contains grammar that is statistically uncommon are separate determinations performed for the utterance transcription.
2. The computer implemented method of claim 1 , further comprising:
reviewing the analyzed utterance.
3. The computer implemented method of claim 1 , further comprising:
determining an analysis efficiency of the utterance analysis.
4. The computer implemented method of claim 1 , further comprising:
updating the utterance analysis based upon the determined difference.
5. The computer implemented method of claim 1 , further comprising:
correlating the analyzed utterance to the translated utterance.
6. The computer implemented method of claim 1 , further comprising:
reporting the determined difference.
7. The computer implemented method of claim 1 , further comprising:
categorizing the determined difference.
8. The computer implemented method of claim 1 , further comprising:
grouping the determined difference.
9. The computer implemented method of claim 1 , further comprising:
tracking the determined difference by a translator.
10. The computer-implemented method of claim 1 , further comprising:
receiving a report of a false acceptance of the transcription from a translator.
11. The computer-implemented method of claim 1 , further comprising:
receiving a report of a false rejection of the transcription from a translator.
12. The computer-implemented method of claim 1 , further comprising:
reporting the determined difference;
categorizing the determined difference;
sorting the determined difference;
grouping the determined difference; and
tracking the determined difference by a translator.
13. The computer-implemented method of claim 1 , further comprising:
sorting the determined difference.
14. A non-transitory computer readable medium comprising instructions that, when executed by a processor, cause the processor to perform a method comprising:
receiving an utterance;
transcribing the utterance;
determining whether the utterance transcription contains grammar that is statistically common;
determining whether the utterance transcription contains grammar that is statistically uncommon;
receiving a translation of the utterance;
determining at least one difference between the transcribed utterance and the translated utterance;
sorting the at least one determined difference; and
reporting the at least one determined difference, wherein
the determining whether the utterance transcription contains grammar that is statistically common and the determining whether the utterance transcription contains grammar that is statistically uncommon are separate determinations performed for the utterance transcription.
15. The computer readable medium of claim 14 , the instructions further configured to cause the processor perform a method comprising:
determining whether the utterance transcription contains grammar that has not previously been transcribed.
16. The computer readable medium of claim 14 , the instructions further configured to cause the processor perform a method comprising:
receiving a report of a correct acceptance of the transcription from a translator.
17. The computer readable medium of claim 14 , the instructions further configured to cause the processor perform a method comprising:
receiving a report of a correct rejection of the transcription from a translator.
18. A system for reporting automatic speech recognition, comprising:
a memory; and
a processor communicably coupled to the memory, wherein the processor is configured to:
receive a transcription of an utterance,
determine whether the utterance transcription contains grammar that is statistically common,
determine whether the utterance transcription contains grammar that is statistically uncommon,
receive a translation of the utterance,
analyze at least one difference between the transcription and the translation,
sort the analyzed at least one difference, and
report the analyzed at least one difference, wherein
the determining whether the utterance transcription contains grammar that is statistically common and the determining whether the utterance transcription contains grammar that is statistically uncommon by the processor are separate determinations performed for the utterance transcription.
19. The system of claim 18 , wherein the translation is performed by a subject matter expert.