Mazin Rahim, Yoshua Bengio, Yann LeCun  Home/Search
Context Related
| att.com/~yann/publ...giolecun97.ps.gz att.com/~yann/exdb...giolecun97.ps.gz Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: att.com/~yann/publis/index (more) Homepages: Y.Lecun |
Rate this article:      (best)Comment on this article |
Abstract: A system for discriminative feature and model design is presented for automatic speech recognition. Training based on minimum classification error with a single objective function is applied for designing a set of parallel networks performing feature transformation and a set of hidden Markov models performing speech recognition. This paper compares the use of linear and non-linear functional transformations when applied to conventional recognition features, such as spectrum or cepstrum. It also ... (Update)
Context of citations to this paper: More
.... in Section VII, can improve performance as this has been clearly shown for speech recognition systems [48] 49] 50] 107] [108]. The Input Output HMM model (IOHMM) 105] 109] is strongly related to graph transformers. Viewed as a probabilistic model, an IOHMM...
.... HMMs also showed marked improvements brought by global training [Bengio et al. 1992a, Bourlard and Morgan, 1994, Bengio, 1996, Rahim et al. 1997a] 7 Multiple Object Recognition: Space Displacement Neural Network . There is a simple alternative to explicitly segmenting...
Cited by: More
Neural Networks in Automatic Speech Recognition - Beaufays, Bourlard, Franco, al. (2001) (Correct)
Nonlinear Discriminant Feature Extraction For Robust.. - Konig, Heck.. (1998) (Correct)
Gradient-Based Learning Applied to Document Recognition - LeCun, Bottou, Bengio.. (1998) (Correct)
Active bibliography (related documents): More All
0.3: Discriminative Training for Speech Recognition - McDermott (1997) (Correct)
0.3: Comparison Of Optimization Methods For.. - Schlüter.. (Correct)
0.2: Adaptation To Environment And Speaker Using.. - Yuk, Flanagan.. (Correct)
Similar documents based on text: More All
0.4: Discriminative Training on language model - Chen, Lee, Li (Correct)
0.4: Comparison of Discriminative Training Criteria and.. - Schlüter, Macherey.. (2001) (Correct)
0.4: Convolutional Networks for Images, Speech, and Time-Series - LeCun, Bengio (1995) (Correct)
Related documents from co-citation: More All
6: Global optimization of a neural network-hidden markov model hybrid - Bengio, De Mori et al. - 1992
5: Discriminative Learning for Minimum Error Classification (context) - Juang, Katagiri - 1992
4: Learning curves: Asymptotic values and rate of convergence (context) - Cortes, Jackel et al. - 1994
BibTeX entry: (Update)
M. Rahim, Y. Bengio, and Y. LeCun, "Discriminative feature and model design for automatic speech recognition," in Proc. of Eurospeech, Rhodes, Greece, 1997. http://citeseer.ist.psu.edu/rahim97discriminative.html More
@inproceedings{ rahim97discriminative,
author = "Mazin Rahim and Yoshua Bengio and Yann LeCun",
title = "Discriminative Feature and Model Design for Automatic Speech Recognition",
booktitle = "Proc. Eurospeech '97",
address = "Rhodes, Greece",
pages = "75--78",
year = "1997",
url = "citeseer.ist.psu.edu/rahim97discriminative.html" }
Citations (may not include all citations):58 Discriminative learning for minimum error classification (context) - Juang, Katagiri - 1992
49 Global optimization of a neural network - hidden Markov mode.. - Bengio, De Mori et al. - 1990
48 Adaptive inverse control (context) - Widrow, Walach - 1995
7 Maximum mutual information of hidden Markov model parameters.. (context) - Bahl, Brown et al. - 1986
4 HMM-based speech recognition using state-dependent (context) - Chengalvarayan, Deng - 1997
4 Simultaneous ANN feature and HMM recognizer design using str.. (context) - Rahim, Lee - 1996
3 Minimum classification error training algorithm for feature .. (context) - Paliwal, Bacchiani et al. - 1995
1 Integrated optimization of feature transformation for speech.. (context) - Euler - 1995
1 Coarticulation models for continuous digit recognition (context) - Pieraccini, Rosenberg - 1990
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.research.att.com/~yann/publis/index.html): More
Reverse TDNN: An Architecture for Trajectory Generation - Simard, Le Cun (Correct)
Reading Checks With Multilayer Graph Transformer Networks - Yann Le (1997) (Correct)
Learning Algorithms For Classification: A.. - LeCun, Jackel.. (1995) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC