This book is a collection of the author’s years of practical experience in teaching and research, in which a comprehensive discussion on the generation, processing, compression, transmission, synthesis, recognition and understanding of speech signals, and a systematical exposition on the front-end processing technology of speech signal, speech coding technology, speech recognition and speaker recognition technologies are fully elaborated. Some commonly-used open source tools for building systems are also introduced in the book, like the HTK tools for HMM systems and Kaldi tools for deep learning systems. This book can be used as teaching materials for senior undergraduate and graduate students from such majors and disciplines in colleges and universities as computer application, signal and information processing, communication and electronic system and etc. It can also be used as reference materials for scientific researchers and engineering technicians in the field.

Han Jiqing is professor and doctoral supervisor of the School of Computer Science and Technology, Harbin Institute of Technology. He has been engaged in teaching and doing scientific research in the fields of speech signal processing and audio information processing.