Our Books
Turn pages, spark change. We inspire, empower and advance learners.
Our Books
Turn pages, spark change. We inspire, empower and advance learners.
Deep Learning: Technology and Practice of Voice Recognition
ByLiu Ruobian

Pub date: April 1, 2019

ISBN: 9787302516927

Rights:

292 p.p.

Description
About Author
Table of Contents
Speech recognition has gradually entered people’s daily life. Such technology is an interdisciplinary subject involving language, computer and mathematics. This book introduces multiple programming language practices (e.g., C#, Perl, Python and Java); employment and code analysis of Kaldi (the open-source speech recognition toolkit); a development environment for deep learning, Convolutional Neural Network, and common language models in speech recognition (e.g., N-tuple model and dependency model), in an aim to help readers quickly understand the basics of speech recognition and master the algorithms for developing speech recognition program. This book starts with the basics of speech recognition, supplemented by informative cases; it is suitable for programmers who need to implement speech recognition, also suitable for students, researchers or practitioners with a background in machine learning or speech recognition.
Liu Ruobian is a core member of the Rabbit Hunting search team and a lecturer of an education and training institution. He had been working at Samsung.