Hierarchical Neural Network Structures for Phoneme Recognition

✍ Scribed by Daniel Vasquez, Rainer Gruhn, Wolfgang Minker (auth.)

• Publisher: Springer-Verlag Berlin Heidelberg
• Year: 2013
• Tongue: English
• Leaves: 146
• Series: Signals and Communication Technology
• Edition: 1
• Category: Library

✦ 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.

✦ Table of Contents

Front Matter....Pages 1-15
Introduction....Pages 1-6
Background in Speech Recognition....Pages 7-30
Phoneme Recognition Task....Pages 31-48
Hierarchical Approach and Downsampling Schemes....Pages 49-59
Extending the Hierarchical Scheme: Inter and Intra Phonetic Information....Pages 61-101
Theoretical Framework for Phoneme Recognition Analysis....Pages 103-117
Summary and Conclusions....Pages 119-122
Back Matter....Pages 0--1

✦ Subjects

Signal, Image and Speech Processing; User Interfaces and Human Computer Interaction; Computational Intelligence; Language Translation and Linguistics