Improvements in Speech Synthesis

E. Keller is the editor of Improvements in Speech Synthesis: Cost 258: The Naturalness of Synthetic Speech, published by Wiley. G. Bailly is the editor of Improvements in Speech Synthesis: Cost 258: The Naturalness of Synthetic Speech, published by Wiley.

• List of Contributors ixPreface xiiiPart I Issues in Signal Generation 11 Towards Greater Naturalness: Future Directions of Research in Speech Synthesis 3Eric Keller2 Towards More Versatile Signal Generation Systems 18GeÂrard Bailly3 A Parametric Harmonic ‡ Noise Model 22GeÂrard Bailly4 The COST 258 Signal Generation Test Array 39GeÂrard Bailly5 Concatenative Text-to-Speech Synthesis Based on Sinusoidal Modelling 52Eduardo RodrõÂguez Banga,Carmen GarcõÂa Mateo and Xavier FernaÂndez Salgado6 Shape Invariant Pitch and Time-Scale Modification of Speech Based on a Harmonic Model 64Darragh O'Brien and Alex Monaghan7 Concatenative Speech Synthesis Using SRELP 76Erhard RankPart II Issues in Prosody 878 Prosody in Synthetic Speech: Problems, Solutions and Challenges 89Alex Monaghan9 State-of-the-Art Summary of European Synthetic Prosody R&D 93Alex Monaghan10 Modelling FO in Various Romance Languages: Implementation in Some TTS Systems 104Philippe Martin11 Acoustic Characterisation of the Tonic Syllable in Portuguese 120JoaÄo Paulo Ramos Teixeira and Diamantino R.S. Freitas12 Prosodic Parameters of Synthetic Czech: Developing Rules for Duration and Intensity 129Marie DohalskaÂ,Jana Mejvaldova and Tomas DubeÏda13 MFGI, a Linguistically Motivated Quantitative Model of German Prosody 134HansjoÈrg Mixdorff14 Improvements in Modelling the FO Contour for Different Types of Intonation Units in Slovene 144Ales Dobnikar15 Representing Speech Rhythm 154Brigitte Zellner Keller and Eric Keller16 Phonetic and Timing Considerations in a Swiss High German TTS System 165Beat Siebenhaar,Brigitte Zellner Keller and Eric Keller17 Corpus-based Development of Prosodic Models Across Six Languages 176Justin Fackrell,Halewijn Vereecken,Cynthia Grover, Jean-Pierre Martens and Bert Van Coile18 Vowel Reduction in German Read Speech 186Christina WideraPart III Issues in Styles of Speech 19719 Variability and Speaking Styles in Speech Synthesis 199Jacques Terken20 An Auditory Analysis of the Prosody of Fast and Slow Speech Styles in English, Dutch and German 204Alex Monaghan21 Automatic Prosody Modelling of Galician and its Application to Spanish 218Eduardo LoÂpez Gonzalo,Juan M. Villar Navarro and Luis A. HernaÂndez GoÂmez22 Reduction and Assimilatory Processes in Conversational French Speech: Implications for Speech Synthesis 228Danielle Duez23 Acoustic Patterns of Emotions 237Branka Zei Pollermann and Marc Archinard24 The Role of Pitch and Tempo in Spanish Emotional Speech: Towards Concatenative Synthesis 246Juan Manuel Montero Martinez,Juana M. GutieÂrrez Arriola, Ricardo de CoÂrdoba Herralde,Emilia Victoria EnrõÂquez Carrasco and Jose Manuel Pardo MunÄoz25 Voice Quality and the Synthesis of Affect 252Ailbhe Nõ Chasaide and Christer Gobl26 Prosodic Parameters of a `Fun' Speaking Style 264Kjell Gustafson and David House27 Dynamics of the Glottal Source Signal: Implications for Naturalness in Speech Synthesis 273Christer Gobl and Ailbhe Nõ Chasaide28 A Nonlinear Rhythmic Component in Various Styles of Speech 284Brigitte Zellner Keller and Eric KellerPart IV Issues in Segmentation and Mark-up 29329 Issues in Segmentation and Mark-up 295Mark Huckvale30 The Use and Potential of Extensible Mark-up �XML) in Speech Generation 297Mark Huckvale31 Mark-up for Speech Synthesis: A Review and Some Suggestions 307Alex Monaghan32 Automatic Analysis of Prosody for Multi-lingual Speech Corpora 320Daniel Hirst33 Automatic Speech Segmentation Based on Alignment with a Text-to-Speech System 328Petr HoraÂk34 Using the COST 249 Reference Speech Recogniser for Automatic Speech Segmentation 339Narada D. Warakagoda and Jon E. NatvigPart V Future Challenges 34935 Future Challenges 351Eric Keller36 Towards Naturalness, or the Challenge of Subjectiveness 353GenevieÁve Caelen-Haumont37 Synthesis Within Multi-Modal Systems 363Andrew Breen38 A Multi-Modal Speech Synthesis Tool Applied to Audio-Visual Prosody 372Jonas Beskow,BjoÈrn GranstroÈm and David House39 Interface Design for Speech Synthesis Systems 383Gudrun FlachIndex 391