Advertisement

Connectionist Speech Recognition

A Hybrid Approach

  • Hervé A. Bourlard
  • Nelson Morgan

Table of contents

  1. Front Matter
    Pages i-xxviii
  2. Background

    1. Front Matter
      Pages 2-2
    2. Hervé A. Bourlard, Nelson Morgan
      Pages 3-13
    3. Hervé A. Bourlard, Nelson Morgan
      Pages 15-25
    4. Hervé A. Bourlard, Nelson Morgan
      Pages 27-58
    5. Hervé A. Bourlard, Nelson Morgan
      Pages 59-80
  3. Hybrid HMM/MLP Systems

    1. Front Matter
      Pages 81-81
    2. Hervé A. Bourlard, Nelson Morgan
      Pages 83-114
    3. Hervé A. Bourlard, Nelson Morgan
      Pages 115-153
    4. Hervé A. Bourlard, Nelson Morgan
      Pages 155-183
    5. Hervé A. Bourlard, Nelson Morgan
      Pages 185-200
    6. Hervé A. Bourlard, Nelson Morgan
      Pages 201-213
    7. Hervé A. Bourlard, Nelson Morgan
      Pages 215-221
    8. Hervé A. Bourlard, Nelson Morgan
      Pages 223-230
  4. Additional Topics

    1. Front Matter
      Pages 231-231
    2. Hervé A. Bourlard, Nelson Morgan
      Pages 233-241
    3. Hervé A. Bourlard, Nelson Morgan
      Pages 243-252
    4. Hervé A. Bourlard, Nelson Morgan
      Pages 253-263
  5. Finale

    1. Front Matter
      Pages 265-265
    2. Hervé A. Bourlard, Nelson Morgan
      Pages 267-274
    3. Hervé A. Bourlard, Nelson Morgan
      Pages 275-280
  6. Back Matter
    Pages 281-313

About this book

Introduction

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.

Keywords

Hardware Markov model Software Standard artificial intelligence classification development hidden markov model network neural networks pattern recognition speech processing speech recognition tables

Authors and affiliations

  • Hervé A. Bourlard
    • 1
    • 2
  • Nelson Morgan
    • 2
    • 3
  1. 1.Lernout & Hauspie Speech ProductsBelgium
  2. 2.International Computer Science InstituteBerkeleyUSA
  3. 3.University of CaliforniaBerkeleyUSA

Bibliographic information

  • DOI https://doi.org/10.1007/978-1-4615-3210-1
  • Copyright Information Kluwer Academic Publishers 1994
  • Publisher Name Springer, Boston, MA
  • eBook Packages Springer Book Archive
  • Print ISBN 978-1-4613-6409-2
  • Online ISBN 978-1-4615-3210-1
  • Series Print ISSN 0893-3405
  • Buy this book on publisher's site