Table of Contents

• Assessing the acceptability of the Smartkom speech synthesis voicesAntje Schweitzer, Norbert Braunschweiler, Grzegorz Dogil, Bernd Möbius. 1-6 [doi]
• Subjective evaluation of join cost & smoothing methodsJithendra Vepa, Simon King. 7-12 [doi]
• Optionality in evaluating prosody predictionErwin Marsi. 13-18 [doi]
• Accurate spectral envelope estimation for articulation-to-speech synthesisYoshinori Shiga, Simon King. 19-24 [doi]
• Formant re-synthesis of dysarthric speechAlexander Kain, Xiaochuan Niu, John-Paul Hosom, Qi Miao, Jan P. H. van Santen. 25-30 [doi]
• Mapping from articulatory movements to vocal tract spectrum with Gaussian mixture model for articulatory speech synthesisTomoki Toda, Alan W. Black, Keiichi Tokuda. 31-36 [doi]
• Using 5 ms segments in concatenative speech synthesisToshio Hirai, Seiichi Tenpaku. 37-42 [doi]
• Unit selection using pitch synchronous cross correlation for Japanese concatenative speech synthesisNobuo Nukaga, Ryota Kamoshida, Kenji Nagamatsu. 43-48 [doi]
• Data-driven perceptually based join costsAnn K. Syrdal, Alistair Conkie. 49-54 [doi]
• Merging data driven and rule based prosodic models for unit selection TTSMatthew P. Aylett. 55-60 [doi]
• Estimating phrase curves in the general superpositional intonation modelJan P. H. van Santen, Taniya Mishra, Esther Klabbers. 61-66 [doi]
• Intonation modeling for TTS using a joint extraction and prediction approachPablo Daniel Agüero, Antonio Bonafonte. 67-72 [doi]
• Clustering of foot-based pitch contours in expressive speechEsther Klabbers, Jan P. H. van Santen. 73-78 [doi]
• A corpus-based approach to expressive speech synthesisEllen Eide, Andrew Aaron, Raimo Bakis, Wael Hamza, Michael A. Picheny, John F. Pitrelli. 79-84 [doi]
• Audiovisual text-to-cued speech synthesisGuillaume Gibert, Gérard Bailly, Frédéric Elisei. 85-90 [doi]
• Synthesising contextually appropriate intonation in limited domainsRachel Baker, Robert A. J. Clark, Michael White. 91-96 [doi]
• Frisian TTS, an example of bootstrapping TTS for minority languagesJelske Dijkstra, Louis C. W. Pols, R. J. J. H. van Son. 97-102 [doi]
• Unit selection voice for Amharic using FestvoxSebsibe H. Mariam, S. Prahallad Kishore, Alan W. Black, Rohit Kumar, Rajeev Sangal. 103-108 [doi]
• Tools for the development of a Hindi speech synthesis systemKalika Bali, Partha Pratim Talukdar, Sridhar Krishna Nemala, A. G. Ramakrishnan. 109-114 [doi]
• A concatenative speech synthesis method using context dependent phoneme sequences with variable length as search unitsHiroyuki Segi, Tohru Takagi, Takayuki Ito. 115-120 [doi]
• Improving pronunciation dictionary coverage of names by modelling spelling variationJustin Fackrell, Wojciech Skut. 121-126 [doi]
• Improving TTS by higher agreement between predicted versus observed pronunciationsYeon-Jun Kim, Ann K. Syrdal, Matthias Jilka. 127-132 [doi]
• A novel discontinuity metric for unit selection text-to-speech synthesisJerome R. Bellegarda. 133-138 [doi]
• Towards phone segmentation for concatenative speech synthesisJordi Adell, Antonio Bonafonte. 139-144 [doi]
• Voice creation for conversational fairy-tale charactersJoakim Gustafson, Kåre Sjölander. 145-150 [doi]
• F0 modeling with multi-layer additive modeling based on a statistical learning techniqueShinsuke Sakai. 151-154 [doi]
• Impact of durational outlier removal from unit selection catalogsJohn Kominek, Alan W. Black. 155-160 [doi]
• Corpus-based synthesis of fundamental frequency contours with various speaking styles from text using F0 contour generation process modelKeikichi Hirose, Kentaro Sato, Nobuaki Minematsu. 161-166 [doi]
• Multi-source based acoustic model for speech synthesisJianhua Tao, Yongguo Kang. 167-172 [doi]
• Festival 2 - build your own general purpose unit selection speech synthesiserRobert A. J. Clark, Korin Richmond, Simon King. 173-178 [doi]
• XIMERA: a new TTS from ATR based on corpus-based technologiesHisashi Kawai, Tomoki Toda, Jinfu Ni, Minoru Tsuzaki, Keiichi Tokuda. 179-184 [doi]
• Prosodic data driven modelling of a narrative style in Festival TTSFabio Tesser, Piero Cosi, Carlo Drioli, Graziano Tisato. 185-190 [doi]
• An introduction of trajectory model into HMM-based speech synthesisHeiga Zen, Keiichi Tokuda, Tadashi Kitamura. 191-196 [doi]
• Duration modeling of Indian languages Hindi and TeluguNemala Sridhar Krishna, Hema A. Murthy. 197-202 [doi]
• Prominence prediction for supersentential prosodic modeling based on a new databaseJason Y. Zhang, Arthur R. Toth, Kevyn Collins-Thompson, Alan W. Black. 203-208 [doi]
• Aligning letters and phonemes for speech synthesisRobert I. Damper, Yannick Marchand, John-David Marseters, Alex Bazin. 209-214 [doi]
• rvoice studio and activepromptsPeter Rutten, David Talkin. 215-216 [doi]
• Language independent phoneme mapping for foreign TTSLeonardo Badino, Claudia Barolo, Silvia Quazza. 217-218 [doi]
• Towards emotional speech synthesis: a rule based approachEnrico Zovato, Alberto Pacchiotti, Silvia Quazza, Stefano Sandri. 219-220 [doi]
• Corpora of latin american Spanish for research in prosody and synthesisAlejandro Renato, José A. Alvarez. 221-222 [doi]
• The CMU Arctic speech databasesJohn Kominek, Alan W. Black. 223-224 [doi]
• Forced alignment for speech synthesis databases using duration and prosodic phrase breaksArthur R. Toth. 225-226 [doi]
• Analysis of fundamental frequency contours of Cantonese based on a command-response modelWentao Gu, Hiroya Fujisaki, Keikichi Hirose. 227-228 [doi]
• Creating a database of speech in noise for unit selection synthesisBrian Langner, Alan W. Black. 229-230 [doi]