The Springer International Series in Engineering and Computer Science

Connectionist Speech Recognition

A Hybrid Approach

Authors: Bourlard, Hervé A., Morgan, Nelson

Free Preview

Buy this book

eBook $169.00
price for USA in USD
  • ISBN 978-1-4615-3210-1
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Hardcover $279.99
price for USA in USD
  • ISBN 978-0-7923-9396-2
  • Free shipping for individuals worldwide
  • Institutional customers should get in touch with their account manager
  • Covid-19 shipping restrictions & severe weather in the US may cause delays
  • Usually ready to be dispatched within 3 to 5 business days, if in stock
Softcover $219.99
price for USA in USD
  • ISBN 978-1-4613-6409-2
  • Free shipping for individuals worldwide
  • Institutional customers should get in touch with their account manager
  • Covid-19 shipping restrictions & severe weather in the US may cause delays
  • Usually ready to be dispatched within 3 to 5 business days, if in stock
About this book

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.

Table of contents (16 chapters)

Table of contents (16 chapters)

Buy this book

eBook $169.00
price for USA in USD
  • ISBN 978-1-4615-3210-1
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Hardcover $279.99
price for USA in USD
  • ISBN 978-0-7923-9396-2
  • Free shipping for individuals worldwide
  • Institutional customers should get in touch with their account manager
  • Covid-19 shipping restrictions & severe weather in the US may cause delays
  • Usually ready to be dispatched within 3 to 5 business days, if in stock
Softcover $219.99
price for USA in USD
  • ISBN 978-1-4613-6409-2
  • Free shipping for individuals worldwide
  • Institutional customers should get in touch with their account manager
  • Covid-19 shipping restrictions & severe weather in the US may cause delays
  • Usually ready to be dispatched within 3 to 5 business days, if in stock
Loading...

Recommended for you

Loading...

Bibliographic Information

Bibliographic Information
Book Title
Connectionist Speech Recognition
Book Subtitle
A Hybrid Approach
Authors
Series Title
The Springer International Series in Engineering and Computer Science
Series Volume
247
Copyright
1994
Publisher
Springer US
Copyright Holder
Springer Science+Business Media New York
eBook ISBN
978-1-4615-3210-1
DOI
10.1007/978-1-4615-3210-1
Hardcover ISBN
978-0-7923-9396-2
Softcover ISBN
978-1-4613-6409-2
Series ISSN
0893-3405
Edition Number
1
Number of Pages
XXIX, 313
Topics