Source Modeling Techniques for Quality Enhancement in Statistical Parametric Speech Synthesis

This book presents a statistical parametric speech synthesis (SPSS) framework for developing a speech synthesis system where the desired speech is generated from the parameters of vocal tract and excitation source. Throughout the book, the authors discuss novel source modeling techniques to enhance the naturalness and overall intelligibility of the SPSS system. This book provides several important methods and models for generating the excitation source parameters for enhancing the overall quality of synthesized speech. The contents of the book are useful for both researchers and system developers. For researchers, the book is useful for knowing the current state-of-the-art excitation source models for SPSS and further refining the source models to incorporate the realistic semantics present in the text. For system developers, the book is useful to integrate the sophisticated excitation source models mentioned to the latest models of mobile/smart phones.

K. Sreenivasa Rao is currently a Professor at IIT Kharagpur, where he has taught since 2007. He has also worked at IIT Guwahati and IIT Madras. He received his PhD from IIT Madras in 2005. He is the author of 8 books, 68 journal articles, 2 patents, 25 book chapters, and 140 conference proceedings.

Narendra N P is a Postdoctoral Researcher at Aalto University. He received his PhD at IIT Kharagpur in 2016. He has published 7 journal articles, 3 book chapters, and 15 conference proceedings.