Automatic Speech Recognition: A Deep Learning Approach

ISBN-13: 9781447169673 / Angielski / Miękka / 2016 / 321 str.

Dong Yu; Li Deng

Opis

This book reviews past and present work on discriminative and hierarchical models for both acoustic and language modeling. It also analyzes the research direction and trends towards establishing future-generation speech recognition.

Recenzje

"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)

Spis treści

Section 1: Automatic speech recognition: Background.- Feature extraction: basic frontend.- Acoustic model: Gaussian mixture hidden Markov model.- Language model: stochastic N-gram.- Historical reviews of speech recognition research: 1st, 2nd, 3rd, 3.5th, and 4th generations.- Section 2: Advanced feature extraction and transformation.- Unsupervised feature extraction.- Discriminative feature transformation.- Section 3: Advanced acoustic modeling.- Conditional random field (CRF) and hidden conditional random field (HCRF).- Deep-Structured CRF.- Semi-Markov conditional random field.- Deep stacking models.- Deep neural network – hidden Markov hybrid model.- Section 4: Advanced language modeling.- Discriminative Language model.- Log-linear language model.- Neural network language model.

Blurb

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.