ISCA Archive SSW 1998
  ISCA Archive
top

3rd ESCA/COCOSDA Workshop on Speech Synthesis

Jenolan Caves House, Blue Mountains, Australia
26-29 November 1998

Dedicated to the memory of Christian Benoit

Session A: Assessment and Standards


Comparison of subjective evaluation and an objective evaluation metric for prosody in text-to-speech synthesis
Daniel Hirst, Albert Rilliard, Véronique Aubergé

Comparing the comprehensibility of different synthetic voices in a dual task experiment
Gerit P. Sonntag, Thomas Portele, Felicitas Haas

Joint evaluation of text-to-speech synthesis in French within the AUPELF ARC-B3 project
Christophe d'Alessandro

Where is the information in speech? (and to what extent can it be modelled in synthesis?)
Nick Campbell

Synthetic speech/sound control language: MSCL
Osamu Mizuno, Shin'ya Nakajima

SABLE: A standard for TTS markup
Richard Sproat, Andrew Hunt, Mari Ostendorf, Paul Taylor, Allan Black, Kevin Lenzo, Mike Edgington

Modeling segmental durations for Japanese text-to-speech synthesis
Jennifer J. Venditti, Jan P. H. van Santen

Contextual Effects on Syllable Duration
Li-Chiung Yang

Modeling phone duration: application to Catalan TTS
Albert Febrer, Jaume Padrell, Antonio Bonafonte

Implications of energy declination for speech synthesis
Jürgen Trouvain, William J. Barry, Claus Nielsen, Ove Andersen

Comparative evaluation of letter-to-sound conversion techniques for English text-to-speech synthesis
Robert I. Damper, Y. Marchand, M. J. Adamson, Kjell Gustafson

Word and syllable models for German text-to-speech synthesis
Bernd Möbius

Improving pronunciation by analogy for text-to-speech applications
Robert I. Damper, Y. Marchand

Multilingual syllabification using weighted finite-state transducers
George Anton Kiraz, Bernd Möbius

Issues in building general letter to sound rules
Alan W Black, Kevin Lenzo, Vincent Pagel

Contextual effects on voicing profiles of German and Mandarin consonants
Chilin Shih, Bernd Möbius

Reiterant speech for the evaluation of natural vs. synthetic prosody
Albert Rilliard, Véronique Aubergé

Designing prosodic databases for automatic modelling in 6 languages
C. Grover, J. Fackrell, H. Vereecken, Jean-Pierre Martens, Bert Van Coile

How a French text-to-speech system can describe loanwords
Frédérique Sannier, Véronique Aubergé, Rabia Belrhali

Efficient adaptation of TTS duration model to new speakers
Chilin Shih, Wentao Gu, Jan P. H. van Santen

Prosody control in fluent Dutch text-to-speech
Arthur Dirksen, Ludmila Menert

Creating an individual speech rhythm: a data driven approach
Oliver Jokisch, Diane Hirschfeld, Matthias Eichner, Rüdiger Hoffmann

Generating pitch accent distributions that show individual and stylistic differences
Janet E. Cahn

Text chunking for prosodic phrasing in French
Philippe Boula de Mareüil, Christophe d'Alessandro

Individuation of postlexical phonology for speech synthesis
Corey Miller

Motivations for the prosodic predictive chain
Eric Keller, Brigitte Zellner

Temporal structures for fast and slow speech rate
Brigitte Zellner

The architecture of the Festival speech synthesis system
Paul Taylor, Alan W. Black, Richard Caley

JUst CONcatenation - A Corpus-based Approach and its Limits
Thomas Portele

Concatenative speech synthesis for European Portuguese
Pedro M. Carvalho, Luís C. Oliveira, Isabel M. Trancoso, M. Céu Viana

Synthesising short vowels from their long counterparts in a concatenative based text-to-speech system
Ove Andersen, N.-J. Dyhr, I. S. Engberg, C. Nielsen

A biphone constrained concatenation method for diphone synthesis
H. Timothy Bunnell, Steven R. Hoskins, Debra M. Yarrington

Foreign Language Speech System
Nick Campbell

Prosody-based unit selection for Japanese speech synthesis
Ken Fujisawa, Nick Campbell

Diphone synthesis using unit selection
Mark Beutnagel, Alistair Conkie, Ann K. Syrdal

Improving speech synthesis of CHATR using a perceptual discontinuity function and constraints of prosodic modification
Wen Ding, Ken Fujisawa, Nick Campbell

Generalization and discrimination in tree-structured unit selection
Michael W. Macon, Andrew E. Cronk, Johan Wouters

Non-uniform unit selection and the similarity metric within BT’s Laureate TTS system
Andrew P. Breen, Peter Jackson

Trying to mimic human segmentation of speech using HMM and fuzzy logic post-correction rules
D. Torre Toledano, M. A. Rodríguez Crespo, J. G. Escalada Sardina

Evaluation of speech synthesis systems for Dutch in telecommunication applications
Agaath Sluijter, E. Bosgoed, J. Kerkhoff, E. Meier, Toni Rietveld, A. Sanderman, Marc Swerts, Jacques Terken

PROCSY: A hybrid approach to high-quality formant synthesis using HLSyn
Sebastian Heid, Sarah Hawkins

Personalizing a speech synthesizer by voice adaptation
Alexander Kain, Mike Macon

Which is more important in a concatenative text to speech system - pitch, duration, or spectral discontinuity?
M. Plumpe, S. Meredith

Estimation of articulatory parameter trajectory from speech acoustic dynamics
C. Silva, S. Chennoukh

An Irish speech synthesiser
L. Charonnat, G. Ó-Néill, Guy Mercier

A three-dimensional linear articulatory model based on MRI data
Pierre Badin, Gérard Bailly, M. Raybaudi, C. Segebarth

On subband analysis based on glottal-ARMAX speech model
Keiichi Funaki, Yoshikazu Miyanaga, Koji Tochinai

Concatenative speech synthesis using a harmonic plus noise model
Yannis Stylianou

Removing phase mismatches in concatenative speech synthesis
Yannis Stylianou

Speaker adaptation for HMM-based speech synthesis system using MLLR
Masatsune Tamura, Takashi Masuko, Keiichi Tokuda, Takao Kobayashi

Experiments in voice quality modification of natural speech signals: the spectral approach
Christophe d’Alessandro, Boris Doval

A wavelet-domain PSOLA approach
Martin Holzapfel, Rüdiger Hoffmann, Harald Höge

Cloning synthetic talking heads
Jialin Zhong, Joseph Olive

Description of the Bell Labs Intonation System
Jan P. H. van Santen, Bernd Möbius, Jennifer J. Venditti, Chilin Shih

A command-response model for F0 contour generation in multilingual speech synthesis
Hiroya Fujisaki, Sumio Ohno, Changfu Wang

Three methods of intonation modeling
Ann K. Syrdal, Gregor Möhler, Kurt Dusterhoff, Alistair Conkie, Alan W. Black

Parametric modeling of intonation using vector quantization
Gregor Möhler, Alistair Conkie

Modeling Japanese boundary pitch movements for speech synthesis
Jennifer J. Venditti, Kazuaki Maeda, Jan P. H. van Santen

Automatic prosody generation using suprasegmental unit selection
F. Malfrère, Thierry Dutoit, Piet Mertens

Report on the Third ESCA TTS Workshop evaluation procedure
Jan P.H. van Santen, Louis C.W. Pols, Masanobu Abe, Dan Kahn, Eric Keller, Julie Vonwiller


×

Session A: Assessment and Standards