Hierarchical Neural Network Structures for Phoneme Recognition

Daniel Vasquez (u. a.)

ISBN 10: 3642344240 / ISBN 13: 9783642344244

Published by Springer-Verlag GmbH, 2012

About this Item

Hierarchical Neural Network Structures for Phoneme Recognition | Daniel Vasquez (u. a.) | Buch | xviii | Englisch | 2012 | Springer-Verlag GmbH | EAN 9783642344244 | Verantwortliche Person für die EU: Springer Verlag GmbH, Tiergartenstr. 17, 69121 Heidelberg, juergen[dot]hartmann[at]springer[dot]com | Anbieter: preigu Print on Demand.

Seller Inventory # 106200002

Bibliographic Details

• Title: Hierarchical Neural Network Structures for Phoneme Recognition
• Publisher: Springer-Verlag GmbH
• Publication Date: 2012
• Language: English
• ISBN 10: 3642344240
• ISBN 13: 9783642344244
• Binding: Buch
• Condition: Neu
• Dimensions: 241W x 160H x 13D millimeters 241 millimeters width by 160 millimeters height by 13 millimeters depth
• Weight: 401 grams
• Seller catalogs:
  • Bücher

About this title

Synopsis

In this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are mainly evaluated within the phoneme recognition task under the Hybrid Hidden Markov Model/Artificial Neural Network (HMM/ANN) paradigm. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron (MLP). Additionally, the output of the first level is used as an input for the second level. This system can be substantially speeded up by removing the redundant information contained at the output of the first level.

From the Back Cover

In this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are evaluated on the phoneme recognition task where a Hybrid Hidden Markov Model/Artificial Neural Network paradigm is used. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron. Additionally, the output of the first level serves as a second level input. The computational speed of the phoneme recognizer can be substantially increased by removing redundant information still contained at the first level output. Several techniques based on temporal and phonetic criteria have been investigated to remove this redundant information. The computational time could be reduced by 57% whilst keeping the system accuracy comparable to the baseline hierarchical approach.