Forced/predictable adaptation for speech recognition

摘要

A method is described for use with automatic speech recognition using discriminative criteria for speaker adaptation. An adaptation evaluation is performed of speech recognition performance data for speech recognition system users. Adaptation candidate users are identified based on the adaptation evaluation for whom an adaptation process is likely to improve system performance.

主权项

1. A computer-implemented method for use with automatic speech recognition using one or more computer processes, the method comprising:
performing, by a computing device, an adaptation evaluation of speech-recognition performance data for a plurality of speech-recognition system users; and identifying, based on the adaptation evaluation, one or more adaptation candidate users for whom an adaptation process is likely to improve system performance, wherein the adaptation evaluation comprises determining a change of an adapted recognition model from an initial recognition model.