Information Services banner Edinburgh Research Archive The University of Edinburgh crest

Edinburgh Research Archive >
Informatics, School of >
Informatics Publications >

Please use this identifier to cite or link to this item: http://hdl.handle.net/1842/4863

This item has been viewed 32 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
master(58).pdf3.1 MBAdobe PDFView/Open
Title: Vocal Attractiveness Of Statistical Speech Synthesisers
Authors: Andraszewicz, Sandra
Yamagishi, Junichi
King, Simon
Issue Date: 2011
Citation: Proc. ICASSP 2011 (Prague, Czech Republic)
Publisher: IEEE
Abstract: Our previous analysis of speaker-adaptive HMM-based speech synthesis methods suggested that there are two possible reasons why average voices can obtain higher subjective scores than any individual adapted voice: 1) model adaptation degrades speech quality proportionally to the distance ‘moved’ by the transforms, and 2) psychoacoustic effects relating to the attractiveness of the voice. This paper is a follow-on from that analysis and aims to separate these effects out. Our latest perceptual experiments focus on attractiveness, using average voices and speaker-dependent voices without model transformation, and show that using several speakers to create a voice improves smoothness (measured by Harmonics-to-Noise Ratio), reduces distance from the the average voice in the log F0-F1 space of the final voice and hence makes it more attractive at the segmental level. However, this is weakened or overridden at supra-segmental or sentence levels.
Description: The European Community’s Seventh Framework Programme (FP7/2007-2013) under Grant agreement 213845 (the EMIME project)
Sponsor(s): European Commission
Keywords: average voice
attractiveness
speaker adaptation
speech synthesis
HMM
URI: http://hdl.handle.net/1842/4863
Appears in Collections:Informatics Publications

Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh 2013, and/or the original authors. Privacy and Cookies Policy