System and method for unsupervised and active learning for automatic speech recognition
A system and method is provided for combining active and unsupervised learning for automatic speech recognition. This process enables a reduction in the amount of human supervision required for training acoustic and language models and an increase in the performance given the transcribed and un-transcribed data.
1. A method comprising:
identifying, in a database of utterances, transcribed utterances and un-transcribed utterances;
ordering transcription candidate utterances from the un-transcribed utterances based on confidence scores of the transcription candidate utterances, to yield a selectively sampled order;
transcribing, via a processor, a top n utterances from the selectively sampled order, to yield additional transcribed utterances and remainder un-transcribed utterances, wherein the remainder un-transcribed utterances are the un-transcribed utterances without the additional transcribed utterances;
receiving human-transcribed utterances, wherein the human-transcribed utterances are selected from the remainder un-transcribed utterances for human transcription based on the confidence scores; and
adding the additional transcribed utterances and the human-transcribed utterances to the database of utterances.
2. The method of claim 1 , further comprising determining the confidence scores using an acoustic model.
3. The method of claim 1 , further comprising determining the confidence scores using a language model.
4. The method of claim 1 , further comprising:
upon adding the additional transcribed utterances to the database of utterances, removing the additional utterances from the un-transcribed utterances.
5. The method of claim 1 , further comprising continuing the identifying, the transcribing, and the adding until a word error rate has converged.
6. The method of claim 1 , wherein the confidence scores of the transcription candidate utterances are associated with an arithmetic mean of confidences scores of words contained within each transcription candidate utterance.
7. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, result in the processor performing operations comprising:
identifying, in a database of utterances, transcribed utterances and un-transcribed utterances;
ordering transcription candidate utterances from the un-transcribed utterances based on confidence scores of the transcription candidate utterances, to yield a selectively sampled order;
transcribing, via a processor, a top n utterances from the selectively sampled order, to yield additional transcribed utterances and remainder un-transcribed utterances, wherein the remainder un-transcribed utterances are the un-transcribed utterances without the additional transcribed utterances;
receiving human-transcribed utterances, wherein the human-transcribed utterances are selected from the remainder un-transcribed utterances for human transcription based on the confidence scores; and
adding the additional transcribed utterances and the human-transcribed utterances to the database of utterances.
8. The system of claim 7 , the computer-readable storage medium having additional instruction stored which result in the operations further comprising determining the confidence scores using an acoustic model.
9. The system of claim 7 , the computer-readable storage medium having additional instruction stored which result in the operations further comprising determining the confidence scores using a language model.
10. The system of claim 7 , the computer-readable storage medium having additional instruction stored which result in the operations further comprising:
upon adding the additional transcribed utterances to the database of utterances, removing the additional utterances from the un-transcribed utterances.
11. The system of claim 7 , the computer-readable storage medium having additional instruction stored which result in the operations further comprising continuing the identifying, the transcribing, and the adding until a word error rate has converged.
12. The system of claim 7 , wherein the confidence scores of the transcription candidate utterances are associated with an arithmetic mean of confidences scores of words contained within each transcription candidate utterance.
13. A computer-readable storage device having instructions stored which, when executed by a computing device, result in the computing device performing operations comprising:
identifying, in a database of utterances, transcribed utterances and un-transcribed utterances;
ordering transcription candidate utterances from the un-transcribed utterances based on confidence scores of the transcription candidate utterances, to yield a selectively sampled order;
transcribing, via a processor, a top n utterances from the selectively sampled order, to yield additional transcribed utterances and remainder un-transcribed utterances, wherein the remainder un-transcribed utterances are the un-transcribed utterances without the additional transcribed utterances;
receiving human-transcribed utterances, wherein the human-transcribed utterances are selected from the remainder un-transcribed utterances for human transcription based on the confidence scores; and
adding the additional transcribed utterances and the human-transcribed utterances to the database of utterances.
14. The computer-readable storage device of claim 13 , having additional instruction stored which result in the operations further comprising determining the confidence scores using an acoustic model.
15. The computer-readable storage device of claim 13 , having additional instruction stored which result in the operations further comprising determining the confidence scores using a language model.
16. The computer-readable storage device of claim 13 , having additional instruction stored which result in the operations further comprising:
upon adding the additional transcribed utterances to the database of utterances, removing the additional utterances from the un-transcribed utterances.
17. The computer-readable storage device of claim 13 , having additional instruction stored which result in the operations further comprising continuing the identifying, the transcribing, and the adding until a word error rate has converged.