© 2015

Automatic Speech Recognition

A Deep Learning Approach

  • Presents important theoretical foundation and practical considerations of using a wide range of deep learning models and methods for automatic speech recognition

  • Reviews past and present work (up to the fall of year 2014) on most impactful work based on deep learning for acoustic modeling in speech recognition

  • Goes deeply into rigorous mathematical and technical descriptions of deep learning methods successful for speech recognition and related areas of applications

  • Analyzes research directions and trends towards establishing future-generation speech recognition based on extending the current deep learning models


Part of the Signals and Communication Technology book series (SCT)

Table of contents

  1. Front Matter
    Pages i-xxvi
  2. Dong Yu, Li Deng
    Pages 1-9
  3. Conventional Acoustic Models

    1. Front Matter
      Pages 11-11
    2. Dong Yu, Li Deng
      Pages 13-21
    3. Dong Yu, Li Deng
      Pages 23-54
  4. Deep Neural Networks

    1. Front Matter
      Pages 55-55
    2. Dong Yu, Li Deng
      Pages 57-77
    3. Dong Yu, Li Deng
      Pages 79-95
  5. Deep Neural Network-Hidden Markov Model Hybrid Systems for Automatic Speech Recognition

    1. Front Matter
      Pages 97-97
    2. Dong Yu, Li Deng
      Pages 117-136
  6. Representation Learning in Deep Neural Networks

    1. Front Matter
      Pages 155-155
    2. Dong Yu, Li Deng
      Pages 193-215
  7. Advanced Deep Models

    1. Front Matter
      Pages 217-217
    2. Dong Yu, Li Deng
      Pages 237-266
    3. Dong Yu, Li Deng
      Pages 267-298

About this book


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.


Adaptive Training Automatic Speech Recognition Computational Network Deep Generative Model Deep Learning Deep Neural Network Distributed Representation Full-Sequence Training Hidden Markov Model LSTM Recurrent Neural Network Transfer Learning

Authors and affiliations

  1. 1.Microsoft ResearchBothellUSA
  2. 2.Microsoft ResearchRedmondUSA

Bibliographic information

Industry Sectors
IT & Software
Oil, Gas & Geosciences


“Deep Learning (DL) has demonstrated a phenomenal success in various AI applications. … This book by two leading experts in Deep Learning is certainly a welcome addition to the literature of the field, particularly in automatic speech recognition. … this book presents a very valuable vista of the state-of-art of Deep Learning, focusing on speech recognition applications.” (Robert Kozma, Mathematical Reviews, September, 2017)

“The book addresses real-world problems of current interest regarding automatic speech recognition. … This book is useful for all researchers working in automatic speech recognition as well as in real-world applications of deep learning.” (Ruxandra Stoean, zbMATH 1356.68004, 2017)