Sciweavers

7288 search results - page 1062 / 1458
» On process rate semantics
Sort
View
ICASSP
2011
IEEE
14 years 10 months ago
Discriminative Training for direct minimization of deletion, insertion and substitution errors
In this paper, we follow the minimum error principle for acoustic modeling and formulate error objectives in insertion, deletion, and substitution separately for minimization duri...
Sunghwan Shin, Ho-Young Jung, Biing-Hwang Juang
181
Voted
ICASSP
2011
IEEE
14 years 10 months ago
Rapid speaker adaptation with speaker adaptive training and non-negative matrix factorization
In this paper, we describe a novel speaker adaptation algorithm based on Gaussian mixture weight adaptation. A small number of latent speaker vectors are estimated with non-negati...
Xueru Zhang, Kris Demuynck, Hugo Van hamme
201
Voted
ICASSP
2011
IEEE
14 years 10 months ago
User selection schemes for maximizing throughput of multiuser MIMO systems using Zero Forcing Beamforming
The performance of a multiuser MIMO broadcast system depends highly on how the users being served are selected from the pool of users requesting service. Though dirty paper coding...
Anh H. Nguyen, Bhaskar D. Rao
ICASSP
2011
IEEE
14 years 10 months ago
Improved models for Mandarin speech-to-text transcription
This paper describes recent advances at LIMSI in Mandarin Chinese speech-to-text transcription. A number of novel approaches were introduced in the different system components. Th...
Lori Lamel, Jean-Luc Gauvain, Viet-Bac Le, Ilya Op...
ICASSP
2011
IEEE
14 years 10 months ago
Maximum likelihood adaptation of histogram equalization with constraint for robust speech recognition
In this paper, we propose a novel feature space adaptation technique to improve the robustness of speech recognition in noisy environments. Histogram equalization (HEQ) is an effe...
Xiong Xiao, Jinyu Li, Engsiong Chng, Haizhou Li
« Prev « First page 1062 / 1458 Last » Next »