Improvements in Speech Synthesis: COST 258: The Naturalness of Synthetic Speech

Improvements in Speech Synthesis: COST 258: The Naturalness of Synthetic Speech

Editor(s): E. Keller, G. Bailly, A. Monaghan, J. Terken, M. Huckvale

Published Online: 25 APR 2002

Print ISBN: 9780471499855

Online ISBN: 9780470845943

DOI: 10.1002/0470845945

About this Book

Naturalness in synthetic speech is one of the most intractable problems in information technology today. Although speech synthesis systems have improved considerably over the last 20 years, they rarely sound entirely like human speakers.

Why is this so, and what can be done about it?
* Prosodic processing must be rendered more varied and more appropriate to the speech situation

* Timing, melodic control and the relationships between the various prosodic parameters need increased attention

* Signal processing systems must be developed and perfected that are capable of generating more than just one voice from a database

* A better understanding must be achieved of what distinguishes one voice from another, and of how speech styles differ between simply reading aloud numbers and sentences and their use in interactive speech

* New evaluation methodologies should be developed to provide objective and subjective measurements of the intelligibility of the synthetic speech and the cognitive load imposed upon the listener by impoverished stimuli

* Adequate text markup systems must be proposed and tested with multiple languages in real-world situations

* Further research is required to integrate speech synthesis systems into larger natural-language processing systems
Improvements in Speech Synthesis presents the latest research in the above areas. Contributors include speech synthesis specialists from 16 countries, with experience in the development of systems for 12 European languages. This volume emerges from a four-year European COST project focussed on "The Naturalness of Synthetic Speech", and will be a valuable text for everyone involved in speech synthesis.

Table of contents

    1. You have free access to this content
  1. Part I: Issues in Signal Generation

    1. Chapter 5

      Concatenative Text-to-Speech Synthesis Based on Sinusoidal Modelling (pages 52–63)

      Eduardo Rodríguez Banga, Carmen García Mateo and Xavier Fernández Salgado

  2. Part II: Issues in Prosody

    1. Chapter 12

      Prosodic Parameters of Synthetic Czech (pages 129–133)

      Marie Dohalská, Jana Mejvaldová and Tomáš Dubĕda

    2. Chapter 17

      Corpus-based Development of Prosodic Models Across Six Languages (pages 176–185)

      Justin Fackrell, Halewijn Vereecken, Cynthia Grover, Jean-Pierre Martens and Bert Van Coile

  3. Part III: Issues in Styles of Speech

    1. Chapter 21

      Automatic Prosody Modelling of Galician and its Application to Spanish (pages 218–227)

      Eduardo López Gonzalo, Juan M. Villar Navarro and Luis A. Hernández Gómez

    2. Chapter 24

      The Role of Pitch and Tempo in Spanish Emotional Speech (pages 246–251)

      Juan Manuel Montero Martínez, Juana M. Gutiérrez Arriola, Ricardo de Córdoba Herralde, Emilia Victoria Enríquez Carrasco and José Manuel Pardo Muñoz

  4. Part IV: Issues in Segmentation and Mark-up

  5. Part V: Future Challenges