Progress in Speech Synthesis

For a machine to convert text into sounds that humans can understand as speech requires an enormous range of components, from abstract analysis of discourse structure to synthesis and modulation of the acoustic output. Work in the field is thus inherently interdisciplinary, involving linguistics, computer science, acoustics, and psychology. This collection of articles by leading researchers in each of the fields involved in text-to-speech synthesis provides a picture of recent work in laboratories throughout the world and of the problems and challenges that remain. By providing samples of synthesized speech as well as video demonstrations for several of the synthesizers discussed, the book will also allow the reader to judge what all the work adds up to -- that is, how good is the synthetic speech we can now produce? Topics covered include: Signal processing and source modeling Linguistic analysis Articulatory synthesis and visual speech Concatenative synthesis and automated segmentation Prosodic analysis of natural speech Synthesis of prosody Evaluation and perception Systems and applications. Front Matter....Pages i-xxii Front Matter....Pages 1-1 Section Introduction. Recent Approaches to Modeling the Glottal Source for TTS....Pages 3-7 Synthesizing Allophonic Glottalization....Pages 9-26 Text-to-Speech Synthesis with Dynamic Control of Source Parameters....Pages 27-39 Modification of the Aperiodic Component of Speech Signals for Synthesis....Pages 41-56 On the Use of a Sinusoidal Model for Speech Synthesis in Text-to-Speech....Pages 57-70 Front Matter....Pages 71-71 Section Introduction. The Analysis of Text in Text -to-Speech Synthesis....Pages 73-75 Language-Independent Data-Oriented Grapheme-to-Phoneme Conversion....Pages 77-89 All-Prosodic Speech Synthesis....Pages 91-108 A Model of Timing for Nonsegmental Phonological Structure....Pages 109-121 A Complete Linguistic Analysis for an Italian Text-to-Speech System....Pages 123-138 Discourse Structural Constraints on Accent in Narrative....Pages 139-156 Homograph Disambiguation in Text-to-Speech Synthesis....Pages 157-172 Front Matter....Pages 173-173 Section Introduction. Talking Heads in Speech Synthesis....Pages 175-178 Section Introduction. Articulatory Synthesis and Visual Speech....Pages 179-184 Speech Models and Speech Synthesis....Pages 185-209 A Framework for Synthesis of Segments Based on Pseudoarticulatory Parameters....Pages 211-220 Biomechanical and Physiologically Based Speech Modeling....Pages 221-234 Analysis-Synthesis and Intelligibility of a Talking Face....Pages 235-246 3D Models of the Lips and Jaw for Visual Speech Synthesis....Pages 247-258 Front Matter....Pages 259-259 Section Introduction. Concatenative Synthesis....Pages 261-262 Front Matter....Pages 259-259 A Mixed Inventory Structure for German Concatenative Synthesis....Pages 263-277 Prosody and the Selection of Source Units for Concatenative Synthesis....Pages 279-292 Optimal Coupling of Diphones....Pages 293-304 Automatic Speech Segmentation for Concatenative Inventory Selection....Pages 305-311 The Aligner: Text-to-Speech Alignment Using Markov Models....Pages 313-323 Front Matter....Pages 325-325 Section Introduction. Prosodic Analysis: A Dual Track?....Pages 327-329 Section Introduction. Prosodic Analysis of Natural Speech....Pages 331-332 Automatic Extraction of F 0 Control Rules Using Statistical Analysis....Pages 333-346 Comparing Approaches to Pitch Contour Stylization for Speech Synthesis....Pages 347-363 Generation of Pauses Within the z-score Model....Pages 365-381 Duration Study for the Bell Laboratories Mandarin Text-to-Speech System....Pages 383-399 Synthesizing German Intonation Contours....Pages 401-415 Effect of Speaking Style on Parameters of Fundamental Frequency Contour....Pages 417-428 Front Matter....Pages 429-429 Section Introduction. Text and Prosody....Pages 431-434 Section Introduction. Phonetic Representations for Intonation....Pages 435-441 Computational Extraction of Lexico-Grammatical Information for Generation of Swedish Intonation....Pages 443-457 Parametric Control of Prosodic Variables by Symbolic Input in TTS Synthesis....Pages 459-475 Prosodic and Intonational Domains in Speech Synthesis....Pages 477-493 Speaking Styles: Statistical Analysis and Synthesis by a Text-to-Speech System....Pages 495-510 Front Matter....Pages 511-511 Section Introduction. Evaluation Inside or Assessment Outside....Pages 513-517 Front Matter....Pages 511-511 A Structured Way of Looking at the Performance of Text-to-Speech Systems....Pages 519-527 Evaluation of a TTS-System Intended for the Synthesis of Names....Pages 529-540 Perception of Synthetic Speech....Pages 541-560 Front Matter....Pages 561-561 Section Introduction. A Brief History of Applications....Pages 563-564 A Modular Architecture for Multilingual Text-to-Speech....Pages 565-573 High-Quality Message-to-Speech Generation in a Practical Application....Pages 575-589 Back Matter....Pages 591-598