2047 search results - page 8 / 410 » The limits of speech recognition |
ICASSP
2008
IEEE
14 years 3 months ago
2008
IEEE
Recently, we successfully developed and reported a new unsupervised online adaptation technique, which jointly compensates for additive and convolutive distortions with vector Tay...
ICASSP
2009
IEEE
14 years 3 months ago
2009
IEEE
We propose a new active learning algorithm to address the problem of selecting a limited subset of utterances for transcribing from a large amount of unlabeled utterances so that ...
ICASSP
2011
IEEE
13 years 9 days ago
2011
IEEE
Duration of phonemic segments provide important cues for distinguishing words in languages such as Arabic. Recently, we proposed a discriminatively estimated joint acoustic, durat...
CSL
2010
Springer
13 years 8 months ago
2010
Springer
We propose a unified global entropy reduction maximization (GERM) framework for active learning and semi-supervised learning for speech recognition. Active learning aims to select...
SPEECH
2011
13 years 3 months ago
2011