Sixth International Conference on Spoken Language Processing
October 16-20, 2000
Keyword-Based Discriminative Training of Acoustic Models
Eric D. Sandness, I. Lee Hetherington
Spoken Language Systems Group,
MIT Laboratory for Computer Science, Cambridge, MA, USA
In this paper, we investigate a new discriminative training technique
which focuses on optimizing a keyword error rate, rather
than the error rate on all words. We hypothesize that improvements
in keyword error rate correlate with improvements in understanding
error rates. Keyword-based discriminative training
is accomplished by modifying a standard minimum classification
error (MCE) training algorithm so that only segments of
speech relevant to keyword errors are used in the acoustic model
training. When both the standard and keyword-based techniques
are used to adjust mixture weights, we find that keyword error
rate reduction compared to baseline maximum likelihood (ML)
trained models is nearly twice as large for the keyword-based approach.
The overall word accuracy is also found to be improved
for keyword-based training, and we run several experiments to
investigate this phenomenon.
Sandness, Eric D. / Hetherington, I. Lee (2000):
"Keyword-based discriminative training of acoustic models",
In ICSLP-2000, vol.3, 135-138.