Sciweavers

ICASSP
2011
IEEE
13 years 3 months ago
Open-set speaker identification in broadcast news
In this paper, we examine the problem of text-independent open-set speaker identification (OS-SI) in broadcast news. Particularly, the impact of the population of registered speak...
Chao Gao, Guruprasad Saikumar, Amit Srivastava, Pr...
ICASSP
2011
IEEE
13 years 3 months ago
Recent development of discriminative training using non-uniform criteria for cross-level acoustic modeling
In this paper, we extend our previous study on discriminative training using non-uniform criteria for speech recognition. The work will put emphasis on how the acoustic modeling i...
Chao Weng, Biing-Hwang Juang
ICASSP
2011
IEEE
13 years 3 months ago
Discriminatively trained Probabilistic Linear Discriminant Analysis for speaker verification
Recently, i-vector extraction and Probabilistic Linear Discriminant Analysis (PLDA) have proven to provide state-of-the-art speaker verification performance. In this paper, the s...
Lukas Burget, Oldrich Plchot, Sandro Cumani, Ondre...
CSL
2010
Springer
14 years 7 days ago
Discriminative training of HMMs for automatic speech recognition: A survey
Recently, discriminative training (DT) methods have achieved tremendous progress in automatic speech recognition (ASR). In this survey article, all mainstream DT methods in speech...
Hui Jiang
ICASSP
2010
IEEE
14 years 11 days ago
Large margin estimation of n-gram language models for speech recognition via linear programming
We present a novel discriminative training algorithm for n-gram language models for use in large vocabulary continuous speech recognition. The algorithm uses large margin estimati...
Vladimir Magdin, Hui Jiang
NIPS
2008
14 years 1 months ago
Generative versus discriminative training of RBMs for classification of fMRI images
Neuroimaging datasets often have a very large number of voxels and a very small number of training cases, which means that overfitting of models for this data can become a very se...
Tanya Schmah, Geoffrey E. Hinton, Richard S. Zemel...
ANNPR
2008
Springer
14 years 2 months ago
Partial Discriminative Training of Neural Networks for Classification of Overlapping Classes
In applications such as character recognition, some classes are heavily overlapped but are not necessarily to be separated. For classification of such overlapping classes, either d...
Cheng-Lin Liu
SEMCO
2007
IEEE
14 years 6 months ago
Large-Margin Discriminative Training of Hidden Markov Models for Speech Recognition
Discriminative training has been a leading factor for improving automatic speech recognition (ASR) performance over the last decade. The traditional discriminative training, howev...
Dong Yu, Li Deng
ICASSP
2009
IEEE
14 years 7 months ago
Generalized Baum-Welch algorithm for discriminative training on large vocabulary continuous speech recognition system
We propose a new optimization algorithm called Generalized Baum Welch (GBW) algorithm for discriminative training on hidden Markov model (HMM). GBW is based on Lagrange relaxation...
Roger Hsiao, Yik-Cheung Tam, Tanja Schultz
ICML
2009
IEEE
15 years 29 days ago
Matrix updates for perceptron training of continuous density hidden Markov models
In this paper, we investigate a simple, mistakedriven learning algorithm for discriminative training of continuous density hidden Markov models (CD-HMMs). Most CD-HMMs for automat...
Chih-Chieh Cheng, Fei Sha, Lawrence K. Saul