4th ISCA Tutorial and Research Workshop on

Atholl Palace Hotel, Perthshire, Scotland

August 29th - September 1st, 2001

Welcome from the chair.

Keynote 1:

• Visual synthesis ( Paper | Presentation )
  Gérard Bailly

Oral Session 1:

• 114: A Discourse Model for Pitch-Range Control
  Gregor Moehler and Joerg Mayer
  
  
• 108: A bilingual speech design tool: Sesign2001
  Masanobu Abe, Osamu Mizuno, Tsubasa Shinozaki, Hideyuki Mizuno and Shin'ya Nakajima
  
  
• 136: Creation of Speech Corpora for the Multilingual Bonn Open Synthesis System
  Esther Klabbers and Karlheinz Stoeber
  
  

Oral Session 2:

• 125: Predicting phrase breaks with memory-based learning
  Bertjan Busser, Walter Daelemans, Antal van den Bosch
  
  
• 137: On the Role of Duration Prediction and Symbolic Representation for the Evaluation of Synthetic Speech
  Caren Brinckmann and Jürgen Trouvain
  
  
• 117: Rare Events and Closed Domains: Two Delicate Concepts in Speech Synthesis
  Bernd Möbius
  
  
• 139: Predicting segmental duration using Bayesian belief networks
  Olga Goubanova
  
  

Oral Session 3:

• 113: Prosodic Unit Selection Using an Imitation Speech Database
  (examples)
  Joram Meron
  
  
• 123: A New Distance Measure for Costing Spectral Discontinuities in Concatenative Speech Synthesisers
  Robert E Donovan
  
  
• 129: Optimal Data Selection for Unit Selection Synthesis
  Alan W Black and Kevin A. Lenzo
  
  
• 118: Definition of a Training Set for Unit Selection-Based Speech Synthesis
  (examples)
  Karlheinz Stöber, Petra Wagner, Esther Klabbers, Wolfgang Hess
  
  
• 122: A Text-to-Speech Platform for Variable Length Optimal Unit Searching Using Perceptual Cost Functions
  Minkyu Lee, Daniel P. Lopresti, Joseph P. Olive

Keynote 2:

• Unit Selection Synthesis
  Yoshinori Sagisaka

Oral Session 4:

• 106:Synthesizing static vowels and dynamic sounds using a 3D vocal tract model
  Olov Engwall
  
  
• 107: Close shadowing natural vs synthetic speech
  Gérard Bailly
  
  
• 142: Automatic Glottal Closed-Phase Location and Analysis by Kalman Filtering
  John G McKenna

Oral Session 5:

• 103 A Pronunciation-by-Analogy Module for the Festival Text-to-Speech Synthesiser
  Robert I. Damper, Craig Z. Stanbridge and Yannick Marchand
  
  
• 131: Bi-directional Conversion Between Graphemes and Phonemes Using a Joint N-gram Model
  Lucian Galescu and James F. Allen
  
  
• 109: Input/Output Normalisation and Linguistic Analysis for a Multilingual Text-To-Speech Synthesis System
  Philippe Boula de Mareüil and Benoît Soulage
  
  
• 102: A Neural Network and a Hybrid Approach for Accent Label Prediction
  Achim F. Mueller and Ruediger Hoffmann

Oral Session 6:

• 116: Prospects for articulatory synthesis: A position paper
  C H Shadle and R I Damper
  
  
• 111: From MBROLA to NU-MBROLA
  Baris Bozkurt, Michel Bagein, Thierry Dutoit
  
  
• 112: The German Text-to-Speech Synthesis System MARY: A Tool for Research, Development and Teaching
  Marc Schröder Jürgen Trouvain
  
  

Oral Session 7:

• 138: A selection/concatenation text-to-speech synthesis system: databases development, system design, comparative evaluation
  Romain Prudon Christophe d'Alessandro
  
  
• 126: Predicting Underlying Pitch Targets for Intonation Modeling
  Xuejing Sun

Posters 1 (Speech Synthesis Systems)

• 201: A Brief Outline of Aculab TTS: Multilingual TTS for Computer Telephony.
  Alex Monoghan
  
  
• 202: Description of the AhoTTS System for the Basque Language.
  Inma Hernaez, Eva Navas, Juan Luis Murugarren, Borja Etxebarria
  
  
• 203: Demo System fo NU-MBROLA concatonator.
  Baris Bozkurt, Michel Bagein, Thierry Dutoit
  
  
• 204: Flite: a small fast run-time synthesis engine.
  Alan W. Black, Kevin A. Lenzo
  
  
• 205: FipsVox: A French TTS based on a syntactic parser.
  Jean-Philippe Goldman, Arnaud Gaudinat, Luka Nerima, Eric Wehrli
  
  
• 206: The DEMOSTHeNES Speech Composer.
  Gerasimos Xydas, Georgios Kouroupetroglou
  
  
• 207: Current Status of the IBM Trainable Speech Synthesis System.
  R. Donovan et al.
  
  
• 208: The UOP Text-to-Speech System for Greek Speech Synthesis.
  P. Stathopoulou-Zois
  
  
• 209: Actor: A Multilingual Unit-Selection Speech Synthesis System.
  Silva Quazza, Laura Donetti, Loreta Moisa, Pier Luigi Salza
  
  

Posters 2 (Scientific)

• 135: A database design for a concatenative speech synthesis system for the disabled
  Akemi Iida, Nick Campbell
  
  
• 141: Linking Form to Meaning: The Expression and Recognition of Emotions Through Prosody
  Li-chiung Yang and Nick Campbell
  
  
• 140: Prosody evaluation as a diagnostic process: subjective vs. objective measurements
  Albert Rilliard Véronique Aubergé
  
  
• 133: Synthesis of Emotional Speech Using Prosodically Balanced VCV Segments
  Yasuhisa Niimi, Masanori Kasamatsu, Takuya Nishinoto and Masahiro Araki
  
  
• 132: Implementing and Evaluating an Integrated Approach to Modeling German Prosody
  Hansjoerg Mixdorff and Oliver Jokisch
  
  
• 130: Hierarchical Structure and Word Strength Predication of Mandarin Prosody
  Greg P. Kochanski Chilin Shih Hongyan Jing
  
  
• 127: Prosodic Phrasing: Machine and Human Evaluation
  M. Céu Viana, Luis C. Oliveira, Ana I. Mata
  
  
• 124: Synthesis of Prosodic Styles
  Chilin Shih Greg P. Kochanski
  
  
• 120: A Multi-lingual System for the Determination of Phonetic Word Stress Using Soft Feature Selection by Neural Networks
  Horst-Udo Hain Hans Georg Zimmermann
  
  
• 115: A Concatenative Mandarin TTS System without Prosody Model and Prosody Modification
  Min Chu, Hu Peng and Eric Chang
  
  
• 110: An implementation and evaluation of two diphone-based synthesizers for Turkish
  Baris Bozkurt and Thierry Dutoit
  
  
• 105: A Metrical Model of Prosody for French TTS
  Alex Monaghan and Fred Sannier

SSW4 Programme Committee 01/03/2002