Automatic Speech Recognition: A Deep Learning Approach

✍ Scribed by Dong Yu, Li Deng (auth.)

• Publisher: Springer-Verlag London
• Year: 2015
• Tongue: English
• Leaves: 329
• Series: Signals and Communication Technology
• Edition: 1
• Category: Library

✦ Synopsis

This book provides a comprehensive overview of the recent advancement in the field of automatic speech recognition with a focus on deep learning models including deep neural networks and many of their variants. This is the first automatic speech recognition book dedicated to the deep learning approach. In addition to the rigorous mathematical treatment of the subject, the book also presents insights and theoretical foundation of a series of highly successful deep learning models.

✦ Table of Contents

Front Matter....Pages i-xxvi
Introduction....Pages 1-9
Front Matter....Pages 11-11
Gaussian Mixture Models....Pages 13-21
Hidden Markov Models and the Variants....Pages 23-54
Front Matter....Pages 55-55
Deep Neural Networks....Pages 57-77
Advanced Model Initialization Techniques....Pages 79-95
Front Matter....Pages 97-97
Deep Neural Network-Hidden Markov Model Hybrid Systems....Pages 99-116
Training and Decoding Speedup....Pages 117-136
Deep Neural Network Sequence-Discriminative Training....Pages 137-153
Front Matter....Pages 155-155
Feature Representation Learning in Deep Neural Networks....Pages 157-175
Fuse Deep Neural Network and Gaussian Mixture Model Systems....Pages 177-191
Adaptation of Deep Neural Networks....Pages 193-215
Front Matter....Pages 217-217
Representation Sharing and Transfer in Deep Neural Networks....Pages 219-235
Recurrent Neural Networks and Related Models....Pages 237-266
Computational Network....Pages 267-298
Summary and Future Directions....Pages 299-315
Back Matter....Pages 317-321

✦ Subjects

Signal, Image and Speech Processing; Engineering Acoustics; Computer Appl. in Social and Behavioral Sciences