✍ Scribed by E. Keller, G. Bailly, A. Monaghan, and J. Terken
No coin nor oath required. For personal study only.
Naturalness in synthetic speech is one of the most intractable problems in information technology today. Although speech synthesis systems have improved considerably over the last 20 years, they rarely sound entirely like human speakers. Why is this so, and what can be done about it? * Prosodic processing must be rendered more varied and more appropriate to the speech situation Timing, melodic control and the relationships between the various prosodic parameters need increased attention Signal processing systems must be developed and perfected that are capable of generating more than just one voice from a database A better understanding must be achieved of what distinguishes one voice from another, and of how speech styles differ between simply reading aloud numbers and sentences and their use in interactive speech * New evaluation methodologies should be developed to provide objective and subjective measurements of the intelligibility of the synthetic speech and the cognitive load imposed upon the listener by impoverished stimuli * Adequate text markup systems must be proposed and tested with multiple languages in real-world situations Further research is required to integrate speech synthesis systems into larger natural-language processing systems Improvements in Speech Synthesis presents the latest research in the above areas. Contributors include speech synthesis specialists from 16 countries, with experience in the development of systems for 12 European languages. This volume emerges from a four-year European COST project focussed on "The Naturalness of Synthetic Speech", and will be a valuable text for everyone involved in speech synthesis.
Cover......Page 1
Contents......Page 5
Lists of Contributors......Page 9
Preface......Page 13
Part1 Issues in Signal Generation......Page 15
Ch1 Towards Greater Naturalness......Page 17
Ch2 Towards More Versatile Signal Generation Systems......Page 32
Ch3 Parametric Harmonic + Noise Model......Page 36
Ch4 COST 258 Signal Generation Test Array......Page 53
Ch5 Concatenative Text-to-Speech Synthesis Based on Sinusoidal Modelling......Page 66
Ch6 Shape Invariant Pitch & Time-Scale Modification of Speech Based on Harmonic Model......Page 78
Ch7 Concatenative Speech Synthesis using SRELP......Page 90
Part2 Issues in Prosody......Page 101
Ch8 Prosody in Synthetic Speech......Page 103
Ch9 State-of-the-Art Summary of European Synthetic Prosody R&D......Page 107
Ch10 Modelling F0 in Various Romance Languages......Page 118
Ch11 Acoustic Characterisation of Tonic Syllable in Portuguese......Page 134
Ch12 Prosodic Parameters of Synthetic Czech......Page 143
Ch13 MFGI, a Linguistically Motivated Quantitative Model of German Prosody......Page 148
Ch14 Improvements in Modelling F0 Contour for Different Types of Intonation Units in Slovence......Page 158
Ch15 Representing Speech Rhythm......Page 168
Ch16 Phonetic & Timing Considerations in Swiss High German TTS System......Page 179
Ch17 Corpus-Based Development of Prosodic Models across 6 Languages......Page 190
Ch18 Vowel Reduction in German Read Speech......Page 200
Part3 Issues in Styles of Speech......Page 211
Ch19 Variability & Speaking Styles in Speech Synthesis......Page 213
Ch20 Auditory Analysis of Prosody of Fast & Slow Speech Styles in English, Dutch & German......Page 218
Ch21 Automatic Prosody Modelling of Galician & its Application to Spanish......Page 232
Ch22 Reduction & Assimilatory Processes in Conversational French Speech Implications for Speech Synthesis......Page 242
Ch23 Acoustic Patterns of Emotions......Page 251
Ch24 Role of Pitch & Tempo in Spanish Emotional Speech......Page 260
Ch25 Voice Quality & Synthesis of Affect......Page 266
Ch26 Prosodic Parameters of "Fun" Speaking Style......Page 278
Ch27 Dynamics of Glottal Source Signal......Page 287
Ch28 Nonlinear Rhythmic Component in Various Styles of Speech......Page 298
Part4 Issues in Segmentation & Mark-Up......Page 307
Ch29 Issues in Segmentation & Mark-Up......Page 309
Ch30 Use & Potential of Extensible Mark-Up (XML) in Speech Generation......Page 311
Ch31 Mark-Up for Speech Synthesis......Page 321
Ch32 Automatic Analysis of Prosody for Multi-Lingual Speech Corpora......Page 334
Ch33 Automatic Speech Segmentation Based on Alignment with Text-to-Speech System......Page 342
Ch34 Using COST 249 Reference Speech Recogniser for Automatic Speech Segmentation......Page 353
Part5 Future Challenges......Page 363
Ch35 Future Challenges......Page 365
Ch36 Towards Naturalness or Challenge of Subjectiveness......Page 367
Ch37 Synthesis within Multi-Modal Systems......Page 377
Ch38 Multi-Modal Speech Synthesis Tool applied to Audio-Visual Prosody......Page 386
Ch39 Interface Design for Speech Synthesis Systems......Page 397
Index......Page 405
📜 SIMILAR VOLUMES
Naturalness in synthetic speech is one of the most intractable problems in information technology today. Although speech synthesis systems have improved considerably over the last 20 years, they rarely sound entirely like human speakers. <br><br> Why is this so, and what can be done about it? <br> *
Издательство John Wiley, 2002, -407 pp.<div class="bb-sep"></div>Making machines speak like humans is a dream that is slowly coming to fruition. When the first automatic computer voices emerged from their laboratories twenty years ago, their robotic sound quality severely curtailed their general use
With a growing need for understanding the process involved in producing and perceiving spoken language, this timely publication answers these questions in an accessible reference. Containing material resulting from many years' teaching and research, Speech Synthesis provides a complete account of t
Издательство Wiley, 2005, -357 pp.<div class="bb-sep"></div>Методы синтеза речи: от простых до unit selection и моделирования просодии. Использование XML-языков. Способы достижения натурального звучания.<div class="bb-sep"></div><strong>I. Current Work</strong><br/>High-Level and Low-Level Synthesis
