490 search results - page 2 / 98 » Speech modeling based on committee-based active learning |
CSL
2010
Springer
13 years 5 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...
MLMI
2005
Springer
13 years 10 months ago
2005
Springer
Abstract. An important step to bring speech technologies into wide deployment as a functional component in man-machine interfaces is to free the users from close-talk or desktop mi...
CVPR
2011
IEEE
13 years 23 days ago
2011
IEEE
Human activity recognition and speech recognition appear to be two loosely related research areas. However, on a careful thought, there are several analogies between activity and ...
ICASSP
2009
IEEE
14 years 2 days 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
2008
IEEE
13 years 11 months ago
2008
IEEE
We are interested in recovering aspects of vocal tract’s geometry and dynamics from auditory and visual speech cues. We approach the problem in a statistical framework based on ...