Data-Driven Techniques in Speech Synthesis

ISBN-13: 9781441947338 / Angielski / Miękka / 2010 / 316 str.

R. I. Damper

Opis

This first review of a new field covers all areas of speech synthesis from text, ranging from text analysis to letter-to-sound conversion. At the leading edge of current research, the concise and accessible book is written by well respected experts in the field.

Spis treści

1. Learning About Speech from Data: Beyond NETtalk; R.I. Damper. 2. Constructing High-Accuracy Letter-to-Phoneme Rules with Machine Learning; G. Bakiri, Th.G. Dietterich. 3. Analogy, the Corpus and Pronunciation; K.P.H. Sullivan. 4. A Hierarchical Lexical Representation for Pronunciation Generation; H. Meng. 5. English Letter-Phoneme Conversion by Stochastic Transducers; R.W.P. Luk, R.I. Damper. 6. Selection of Multiphone Synthesis Units and Grapheme-to-Phoneme Transcription using Variable-Length Modeling of Strings; S. Deligne, et al. 7. TREETALK: Memory-Based Word Phonemisation; W. Daelemans, A. van den Bosch. 8. Learnable Phonetic Representations in a Connectionist TTS System - I: Text to Phonetics; A.D. Cohen. 9. Using the Tilt Intonation Model: A Data-Driven Approach; A.W. Black, et al. 10. Estimation of Parameters for the Klatt Synthesizer from a Speech Database; J. Coleman, A. Slater. 11. Training Accent and Phrasing Assignment on Large Corpora; J. Hirschberg. 12. Learnable Phonetic Representations in a Connectionist TTS System - II: Phonetics to Speech; A.D. Cohen.