โ Scribed by Robert I. Damper (auth.), Robert I. Damper (eds.)
No coin nor oath required. For personal study only.
Data-Driven Techniques in Speech Synthesis gives a first review of this new field. All areas of speech synthesis from text are covered, including text analysis, letter-to-sound conversion, prosodic marking and extraction of parameters to drive synthesis hardware.
Fuelled by cheap computer processing and memory, the fields of machine learning in particular and artificial intelligence in general are increasingly exploiting approaches in which large databases act as implicit knowledge sources, rather than explicit rules manually written by experts. Speech synthesis is one application area where the new approach is proving powerfully effective, the reliance upon fragile specialist knowledge having hindered its development in the past. This book provides the first review of the new topic, with contributions from leading international experts.
Data-Driven Techniques in Speech Synthesis is at the leading edge of current research, written by well respected experts in the field. The text is concise and accessible, and guides the reader through the new technology. The book will primarily appeal to research engineers and scientists working in the area of speech synthesis. However, it will also be of interest to speech scientists and phoneticians as well as managers and project leaders in the telecommunications industry who need an appreciation of the capabilities and potential of modern speech synthesis technology.
Front Matter....Pages i-xviii
Learning About Speech from Data: Beyond NETtalk....Pages 1-25
Constructing High-Accuracy Letter-to-Phoneme Rules with Machine Learning....Pages 27-44
Analogy, the Corpus and Pronunciation....Pages 45-70
A Hierarchical Lexical Representation for Pronunciation Generation....Pages 71-90
English Letter-Phoneme Conversion by Stochastic Transducers....Pages 91-123
Selection of Multiphone Synthesis Units and Grapheme-to-Phoneme Transcription Using Variable-Length Modeling of Strings....Pages 125-147
Treetalk: Memory-Based Word Phonemisation ....Pages 149-174
Learnable Phonetic Representations in a Connectionist TTS System โ I: Text to Phonetics....Pages 175-197
Using the Tilt Intonation Model: A Data-Driven Approach....Pages 199-214
Estimation of Parameters for the Klatt Synthesizer from a Speech Database....Pages 215-238
Training Accent and Phrasing Assignment on Large Corpora....Pages 239-273
Learnable Phonetic Representations in a Connectionist TTS System โ II: Phonetics to Speech....Pages 275-282
Back Matter....Pages 283-316
Signal, Image and Speech Processing; Computational Linguistics; Phonology; Artificial Intelligence (incl. Robotics)
๐ 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> *
<p><p>This book presents a statistical parametric speech synthesis (SPSS) framework for developing a speech synthesis system where the desired speech is generated from the parameters of vocal tract and excitation source. Throughout the book, the authors discuss novel source modeling techniques to en
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 pro
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
ะะทะดะฐัะตะปัััะฒะพ 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