23201 search results - page 4296 / 4641 » Rewriting Systems with Data |
204
click to vote
ICASSP
2011
IEEE
14 years 10 months ago
2011
IEEE
Unsupervised acoustic model training has been successfully used to improve the performance of automatic speech recognition systems when only a small amount of manually transcribed...
162
click to vote
ICASSP
2011
IEEE
14 years 10 months ago
2011
IEEE
Constrained cepstral systems, which select frames to match various linguistic “constraints” in enrollment and test, have shown significant improvements for speaker verificatio...
184
click to vote
ICASSP
2011
IEEE
14 years 10 months ago
2011
IEEE
Previously we have proposed different models for estimating articulatory gestures and vocal tract variable (TV) trajectories from synthetic speech. We have shown that when deploye...
178
click to vote
ICASSP
2011
IEEE
14 years 10 months ago
2011
IEEE
Long-span language models that capture syntax and semantics are seldom used in the first pass of large vocabulary continuous speech recognition systems due to the prohibitive sea...
165
click to vote
ICASSP
2011
IEEE
14 years 10 months ago
2011
IEEE
Speaker identification is a well-established research problem but has not been a major application used in gaming scenarios. In this paper, we propose a new algorithm for the ope...