Source Modeling Techniques for Quality Enhancement in Statistical Parametric Speech Synthesis

  • K. Sreenivasa Rao
  • N. P.  Narendra

Part of the SpringerBriefs in Speech Technology book series (BRIEFSSPEECHTECH)

Table of contents

  1. Front Matter
    Pages i-xii
  2. K. Sreenivasa Rao, N. P. Narendra
    Pages 1-10
  3. K. Sreenivasa Rao, N. P. Narendra
    Pages 11-27
  4. K. Sreenivasa Rao, N. P. Narendra
    Pages 29-52
  5. K. Sreenivasa Rao, N. P. Narendra
    Pages 53-74
  6. K. Sreenivasa Rao, N. P. Narendra
    Pages 75-103
  7. K. Sreenivasa Rao, N. P. Narendra
    Pages 105-124
  8. K. Sreenivasa Rao, N. P. Narendra
    Pages 125-129
  9. Back Matter
    Pages 131-136

About this book


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.
  • Presents the efficient excitation source modeling techniques for generating high quality speech;
  • Includes a combination of both waveform and parametric methods to enhance the quality of synthesis;
  • Features and methods that need less memory and computational requirements than others, allowing them to be integrated to smart phones and smaller devices.


Statistical parametric speech synthesis (SPSS) HMM-Based speech synthesis (HTS) Excitation source model Robust voicing detection Text-to-speech synthesis (TTS) Hybrid source models/methods Time-domain deterministic plus noise model Zero-frequency filtering method

Authors and affiliations

  • K. Sreenivasa Rao
    • 1
  • N. P.  Narendra
    • 2
  1. 1.Department of Computer Science and EngineeringIndian Institute of Technology KharagpurKharagpurIndia
  2. 2.Aalto UniversityEspooFinland

Bibliographic information

  • DOI
  • Copyright Information The Author(s), under exclusive licence to Springer Nature Switzerland AG 2019
  • Publisher Name Springer, Cham
  • eBook Packages Engineering Engineering (R0)
  • Print ISBN 978-3-030-02758-2
  • Online ISBN 978-3-030-02759-9
  • Series Print ISSN 2191-737X
  • Series Online ISSN 2191-7388
  • Buy this book on publisher's site
Industry Sectors
IT & Software
Oil, Gas & Geosciences