Overview
- Developes a set of five universal perceptual quality dimensions for TTS signals
- Introduces a test protocol for the assessment of the five dimensions in a listening test
- Investigates factors influencing the five perceptual quality dimensions
- Presents different approaches towards instrumental quality assessment of synthetic speech.
- Examines the integration of an instrumental quality assessment model into a TTS system for quality improvement
- Includes supplementary material: sn.pub/extras
Part of the book series: T-Labs Series in Telecommunication Services (TLABS)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
About this book
This book reviews research towards perceptual quality dimensions of synthetic speech, compares these findings with the state of the art, and derives a set of five universal perceptual quality dimensions for TTS signals. They are: (i) naturalness of voice, (ii) prosodic quality, (iii) fluency and intelligibility, (iv) absence of disturbances, and (v) calmness. Moreover, a test protocol for the efficient indentification of those dimensions in a listening test is introduced. Furthermore, several factors influencing these dimensions are examined. In addition, different techniques for the instrumental quality assessment of TTS signals are introduced, reviewed and tested. Finally, the requirements for the integration of an instrumental quality measure into a concatenative TTS system are examined.
Similar content being viewed by others
Keywords
Table of contents (8 chapters)
Authors and Affiliations
Bibliographic Information
Book Title: Quality of Synthetic Speech
Book Subtitle: Perceptual Dimensions, Influencing Factors, and Instrumental Assessment
Authors: Florian Hinterleitner
Series Title: T-Labs Series in Telecommunication Services
DOI: https://doi.org/10.1007/978-981-10-3734-4
Publisher: Springer Singapore
eBook Packages: Engineering, Engineering (R0)
Copyright Information: Springer Nature Singapore Pte Ltd. 2017
Hardcover ISBN: 978-981-10-3733-7Published: 18 April 2017
Softcover ISBN: 978-981-10-9953-3Published: 29 July 2018
eBook ISBN: 978-981-10-3734-4Published: 07 April 2017
Series ISSN: 2192-2810
Series E-ISSN: 2192-2829
Edition Number: 1
Number of Pages: XVI, 157
Number of Illustrations: 29 b/w illustrations
Topics: Signal, Image and Speech Processing, User Interfaces and Human Computer Interaction