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.

Table of Contents:
I Signal Processing and Source Modeling.- 1 Section Introduction. Recent Approaches to Modeling the Glottal Source for TTS.- 2 Synthesizing Allophonic Glottalization.- 3 Text-to-Speech Synthesis with Dynamic Control of Source Parameters.- 4 Modification of the Aperiodic Component of Speech Signals for Synthesis.- 5 On the Use of a Sinusoidal Model for Speech Synthesis in Text-to-Speech.- II Linguistic Analysis.- 6 Section Introduction. The Analysis of Text in Text-to-Speech Synthesis.- 7 Language-Independent Data-Oriented Grapheme-to-Phoneme Conversion.- 8 All-Prosodic Speech Synthesis.- 9 A Model of Timing for Nonsegmental Phonological Structure.- 10 A Complete Linguistic Analysis for an Italian Text-to-Speech System.- 11 Discourse Structural Constraints on Accent in Narrative.- 12 Homograph Disambiguation in Text-to-Speech Synthesis.- III Articulatory Synthesis and Visual Speech.- 13 Section Introduction. Talking Heads in Speech Synthesis.- 14 Section Introduction. Articulatory Synthesis and Visual Speech.- 15 Speech Models and Speech Synthesis.- 16 A Framework for Synthesis of Segments Based on Pseudoarticulatory Parameters.- 17 Biomechanical and Physiologically Based Speech Modeling.- 18 Analysis-Synthesis and Intelligibility of a Talking Face.- 19 3D Models of the Lips and Jaw for Visual Speech Synthesis.- IV Concatenative Synthesis and Automated Segmentation.- 20 Section Introduction. Concatenative Synthesis.- 21 A Mixed Inventory Structure for German Concatenative Synthesis.- 22 Prosody and the Selection of Source Units for Concatenative Synthesis.- 23 Optimal Coupling of Diphones.- 24 Automatic Speech Segmentation for Concatenative Inventory Selection.- 25 The Aligner: Text-to-Speech Alignment Using Markov Models.- V Prosodic Analysis of Natural Speech.- 26 Section Introduction. Prosodic Analysis: A Dual Track?.- 27 Section Introduction. Prosodic Analysis of Natural Speech.- 28 Automatic Extraction of F0 Control Rules Using Statistical Analysis.- 29 Comparing Approaches to Pitch Contour Stylization for Speech Synthesis.- 30 Generation of Pauses Within the z-score Model.- 31 Duration Study for the Bell Laboratories Mandarin Text-to-Speech System.- 32 Synthesizing German Intonation Contours.- 33 Effect of Speaking Style on Parameters of Fundamental Frequency Contour.- VI Synthesis of Prosody.- 34 Section Introduction. Text and Prosody.- 35 Section Introduction. Phonetic Representations for Intonation.- 36 Computational Extraction of Lexico-Grammatical Information for Generation of Swedish Intonation.- 37 Parametric Control of Prosodic Variables by Symbolic Input in TTS Synthesis.- 38 Prosodic and Intonational Domains in Speech Synthesis.- 39 Speaking Styles: Statistical Analysis and Synthesis by a Text-to-Speech System.- VII Evaluation and Perception.- 40 Section Introduction. Evaluation Inside or Assessment Outside?.- 41 A Structured Way of Looking at the Performance of Text-to-Speech Systems.- 42 Evaluation of a TTS-System Intended for the Synthesis of Names.- 43 Perception of Synthetic Speech.- VIII Systems and Applications.- 44 Section Introduction. A Brief History of Applications.- 45 A Modular Architecture for Multilingual Text-to-Speech.- 46 High-Quality Message-to-Speech Generation in a Practical Application.