A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is
Automatic Speech Recognition systems integrate three main knowledge sources: acoustic models, pronunciation dictionary and language models. In contrast to common practices, where each source is optimized independently, then combined in a finite-state search space, we investigate here a training procedure which attempts to adjust (some of) the parameters after, rather than before, combination. To this end, we adapted a discriminative training procedure originally devised for language models todoi:10.21437/interspeech.2005-13 fatcat:k5uffqohbravnkbummawwk4vv4