Connectionist Speech Recognition: A Hybrid Approach

Front Cover
Springer Science & Business Media, 1994 - Science - 312 pages
0 Reviews
Connectionist Speech Recognition: A Hybrid Approach describes the theory and implementation of a method to incorporate neural network approaches into state of the art continuous speech recognition systems based on hidden Markov models (HMMs) to improve their performance. In this framework, neural networks (and in particular, multilayer perceptrons or MLPs) have been restricted to well-defined subtasks of the whole system, i.e. HMM emission probability estimation and feature extraction.
The book describes a successful five-year international collaboration between the authors. The lessons learned form a case study that demonstrates how hybrid systems can be developed to combine neural networks with more traditional statistical approaches. The book illustrates both the advantages and limitations of neural networks in the framework of a statistical systems.
Using standard databases and comparison with some conventional approaches, it is shown that MLP probability estimation can improve recognition performance. Other approaches are discussed, though there is no such unequivocal experimental result for these methods.
Connectionist Speech Recognition is of use to anyone intending to use neural networks for speech recognition or within the framework provided by an existing successful statistical approach. This includes research and development groups working in the field of speech recognition, both with standard and neural network approaches, as well as other pattern recognition and/or neural network researchers. The book is also suitable as a text for advanced courses on neural networks or speech processing.
  

What people are saying - Write a review

We haven't found any reviews in the usual places.

Contents

INTRODUCTION
vii
STATISTICAL PATTERN CLASSIFICATION
xix
HIDDEN MARKOV MODELS
1
MULTILAYER PERCEPTRONS
33
SPEECH RECOGNITION USING ANNs
57
STATISTICAL INFERENCE IN MLPs
89
THE HYBRID HMMMLP APPROACH
129
EXPERIMENTAL SYSTEMS
159
TRAINING HARDWARE AND SOFTWARE
197
CROSSVALIDATION IN MLP TRAINING
207
HMMMLP AND PREDICTIVE MODELS
217
FEATURE EXTRACTION BY MLP
227
FINAL SYSTEM OVERVIEW
241
CONCLUSIONS
249
Bibliography
255
Index
281

CONTEXTDEPENDENT MLPs
175
SYSTEM TRADEOFFS
189

Common terms and phrases

Popular passages

Page v - Truth scarce ever yet carried it by vote anywhere at its first appearance: new opinions are always suspected and usually opposed, without any other reason but because they are not already common.

References to this book

All Book Search results »

About the author (1994)

Herve Bourlard is Director of the Idiap Research Institute in Switzerland, Professor at the Swiss Federal Institute of Technology at Lausanne (EPFL) and founding Director of the Swiss National Center of Competence in Research on Interactive Multimodal Information Management (NCCR IM2). He has over 250 publications, has initiated and coordinated numerous international research projects and is the recipient of several scientific and entrepreneurship awards.