The full workshop proceedings is available as single .pdf file: ssw5_proceedings.pdf (10MB), the individual papers and linked into the program below.

• Monday Tuesday Wednesday
• Monday 14th
  • 10:00- Registration opens
  • 1:00-1:30 Welcome and Opening Announcements
  • 1:30-3:00 Oral Session 1
    • 1:30-2:00 1025 "Assessing the Acceptability of the Smartkom Speech Synthesis Voices" by Antje Schweitzer, Norbert Braunschweiler, Grzegorz Dogil, Bernd Mobius
    • 2:00-2:30 1027 "Subjective Evaluation of Join Cost and Smoothing Methods", by Jithendra Vepa, Simon King
    • 2:30-3:00 1039 "Optionality in Evaluating Prosody Prediction", by Erwin Marsi
  • 3:00-3:30 Coffee
  • 3:30-5:00 Oral Session 2
    • 3:30-4:00 1041 "Accurate Spectral Envelope Estimation for Articulation-to-Speech Synthesis" by Yoshinori Shiga, Simon King
    • 4:00-4:30 1052 "Formant Re-Synthesis of Dysarthric Speech" by Alexander Kain, Xiaochuan Niu, John-Paul Hosom, Qi Miao, Jan van Santen
    • 4:30-5:00 1064 "Mapping from Articulatory Movements to Vocal Tract Spectrum with Gaussian Mixture Model for Articulatory Speech Synthesis", by Tomoki Toda, Alan W Black, Keiichi Tokuda
  • 5:00-6:00 Short Paper Posters
    • 2025 "rVoice Studio and ActivePrompts" by Peter Rutten, David Talkin
    • 2026 "Language independent phoneme mapping for foreign TTS" by Leonardo Badino, Claudia Barolo, Silvia Quazza
    • 2027 "Towards emotional speech synthesis: a rule based approach" by Enrico Zovato, Alberto Pacchiotti, Silvia Quazza, Stefano Sandri
    • 2028 "Corporoa of Latin American Spanish for research in prosody and synthesis" by Alejandro Renato, Jose Alvarez
    • 2029 "CMU ARCTIC SPEECH DATABASES" by John Kominek, Alan W Black
    • 2030 "Forced Alignment for speech synthesis using duration and prosodic phrase breaks" by Arthur Toth
    • 2031 "Analysis of fundamental frequency contours of cantonese based on a command response model" by Wentao Gu, Hiroya Fujisaki, Keikichi Hirose
    • 2032 "Creating a Database of Speech in Noise for Unit Selection Synthesis" by Brian Langner, Alan W Black
  • 6:30 Dinner
• Tuesday 15th June
  • 9:00-10:30 Lightning Talks: 5 Minutes each, topics TBA and volunteers requested
  • 10:30-11:00 Coffee
  • 11:00-12:30 Oral Session 3
    • 11:00-11:30 1032 "Using 5 ms segments in concatenative speech synthesis" by Toshio Hirai, Seiichi Tenpaku
    • 11:30-12:00 1033 "Unit Selection using pitch synchronous cross correlation for Japanese concatenative speech synthesis", by Nobuo Nukaga, Ryota Kamoshida, Kenji Nagamatsu
    • 12:00-12:30 1043 "Data-Driven Perceptually-Based Join Costs", Ann K. Syrdal, Alistair D. Conkie
  • 12:30-1:30 Lunch
  • 1:30-3:00 Poster Session 1
    • 1026 "Synthesising Contextually Appropriate Intonation in Limited Domains", by Rachel Baker, Robert A. J. Clark, Michael White
    • 1029 "Frisian TTS, an Example of Bootstrapping TTS for minority Languages", by Jelske Dijkstra, R.J.J.H. van Son, Louis C.W. Pols
    • 1065 "Unit Selection Voice for Amharic Using Festvox", by Sebsibe H/Mariam, S P Kishore, Alan W Black, Rohit Kumar, Rajeev Sangal
    • 1042 "Tools for the Development of a Hindi Speech Synthesis System", by A.G. Ramakrishnan, Kalika Bali, Partha Pratim Talukdar, N. Sridhar Krishna
    • 1038 "A concatenative Speech Synthesis Method using context dependent phoneme sequences with variable length as search units", by Hiroyuki Segi, Tohru Takagi
    • 1040 "Improving Pronunciation Dictionary Coverage Of Names By Modelling Spelling Variation", by Justin Fackrell, Wojciech Skut
    • 1044 "Improving TTS by higher agreement between predicted versus observed pronunciations", by Yeon-Jun Kim, Ann Syrdal, Matthias Jilka
    • 1046 "A Novel Discontinuity Metric for Unit Selection Text-to-Speech Synthesis", by Jerome R. Bellegarda
    • 1048 "Toward Phone Segmentation for Concatenative Speech Synthesis", by Jordi Adell, Antonio Bonafonte
    • 1050 "Voice Creation for Conversational Fairy-Tale Characters", by Kare Sjolander, Joakim Gustafson
  • 12:30-1:30 Lunch
  • 3:30-5:00 Oral Session 4
    • 3:30-4:00 1028 "Merging Data Driven and Rule Based Prosodic Models for Unit Selection TTS", by Matthew Aylett
    • 4:00-4:30 1037 "Estimating Phrase Curves in the General Superpositional Intonation Model" by Jan P.H. van Santen, Taniya Mishra, Esther Klabbers
    • 4:30-5:00 1045 "Intonation Modeling for TTS using a Joint Extraction and Prediction Approach" Pablo Daniel Aguero, Antonio Bonafonte
  • 5:00-6:00 Panel Session: "What do we need for better speech synthesis"
  • 6:30 Dinner
• Wednesday 16th June
  • 9:00-9:45 Tutorial: Overview of Voice Building by Alan W Black
  • 9:45-10:30 Tutorial: Overview of Voice Conversion by Tomoki Toda
  • 10:30-11:00 Coffee
  • 11:00-12:30 Poster Session 2
    • 1053 "F0 Modeling with Multi-Layer Additive Modeling Based on a Statistical Learning Technique", by Shinsuke Sakai
    • 1054 "Impact of Durational Outlier Removal from Unit Selection Catalogs", by John Kominek, Alan W Black
    • 1055 "Corpus-Based Synthesis of Fundamental Frequency Contours with Various Speaking Styles from Text Using F0 Contour Generation Process Model", by Keikichi Hirose, Kentaro Sato, Nobuaki Minematsu
    • 1056 "Multi-Source Based Acoustic Model for Speech Synthesis", by Jianhua Tao, Yongguo Kang
    • 1047 "Festival 2 - Build Your Own General Purpose Unit Selection Speech Synthesiser", by Robert A. J. Clark, Korin Richmond, Simon King
    • 1057 "Ximera: A New TTS from ATR Based on Corpus-Based Technologies", by Hisashi Kawai, Tomoki Toda, Jinfu Ni, Minoru Tsuzaki, Keiichi Tokuda
    • 1060 "Prosodic Data Driven Modelling of a Narrative Style in Festival TTS", by Fabio Tesser, Piero Cosi, Carlo Drioli, Graziano Tisato
    • 1061 "An introduction of trajectory model into HMM-based speech synthesis", by Heiga Zen, Keiichi Tokuda, Tadashi Kitamura
    • 1063 "Duration Modeling of Indian languages Hindi and Telugu. ", by N. Sridhar Krishna, Hema A. Murthy.
    • 1066 "Prominence Prediction for Super-sentential Prosodic Modeling Based on a new Database", by Jason Y Zhang, Arthur R Toth, Kevyn Collins-Thompson, Alan W Black
    • 1070 "Aligning letters and phonemes for speech synthesis", by Robert Damper, Yannick Marchand, John-David Marsters, Alex Bazin
• 12:30-1:30 Lunch
• 1:30-3:00 Oral session 5
  • 1:30-2:00 1051 "Clustering of foot-based pitch contours in expressive speech", by Esther Klabbers, Jan P.H. van Santen
  • 2:00-2:30 1049 "A Corpus-Based Approach to <AHEM/> Expressive Speech Synthesis Authors" by E. Eide, A. Aaron, R. Bakis, W. Hamza, M, Picheny, J. Pitrelli
  • 2:30-3:00 1058 "Audovisual Text-to-Cued Speech Synthesis", by Guillaume Gibert, Gerard Bailly, Frederic Elisei
• 3:00-4:00 Town Hall Meeting / Closing Remarks