Automatic Speech Recognition: A Deep Learning Approach

Introduction
Part - 1: Conventional Acoustic Models
Gaussian Mixture Models
Hidden Markov Models and the Variants
Part - 2: Deep Neural Networks
Deep Neural Networks
Advanced Model Initialization Techniques
Part - 3: Deep Neural Network Hidden Markov Model Hybrid Systems for Automatic Speech Recognition
Deep Neural Network Hidden Markov Model Hybrid Systems
Training and Decoding Speedup
Deep Neural Network Sequence Discriminative Training
Part - 4: Representation Learning in Deep Neural Networks
Feature Representation Learning in Deep Neural Networks
Fuse Deep Neural Network and Gaussian Mixture Model Systems
Adaptation of Deep Neural Networks
Part - 5: Advanced Deep Models
Representation Sharing and Transfer in Deep Neural Networks
Recurrent Neural Networks and Related Models
Computational Network
Summary and Future Directions
Index