Book contents
- Frontmatter
- Contents
- Foreword
- Preface
- 1 Introduction
- 2 Communication and language
- 3 The text-to-speech problem
- 4 Text segmentation and organisation
- 5 Text decoding: finding the words from the text
- 6 Prosody prediction from text
- 7 Phonetics and phonology
- 8 Pronunciation
- 9 Synthesis of prosody
- 10 Signals and filters
- 11 Acoustic models of speech production
- 12 Analysis of speech signals
- 13 Synthesis techniques based on vocal-tract models
- 14 Synthesis by concatenation and signal-processing modification
- 15 Hidden-Markov-model synthesis
- 16 Unit-selection synthesis
- 17 Further issues
- 18 Conclusion
- Appendix A Probability
- Appendix B Phone definitions
- References
- Index
Preface
Published online by Cambridge University Press: 25 January 2011
- Frontmatter
- Contents
- Foreword
- Preface
- 1 Introduction
- 2 Communication and language
- 3 The text-to-speech problem
- 4 Text segmentation and organisation
- 5 Text decoding: finding the words from the text
- 6 Prosody prediction from text
- 7 Phonetics and phonology
- 8 Pronunciation
- 9 Synthesis of prosody
- 10 Signals and filters
- 11 Acoustic models of speech production
- 12 Analysis of speech signals
- 13 Synthesis techniques based on vocal-tract models
- 14 Synthesis by concatenation and signal-processing modification
- 15 Hidden-Markov-model synthesis
- 16 Unit-selection synthesis
- 17 Further issues
- 18 Conclusion
- Appendix A Probability
- Appendix B Phone definitions
- References
- Index
Summary
I'd like to say that Text-to-Speech Synthesis was years in the planning but nothing could be further from the truth. In mid 2004, as Rhetorical Systems was nearing its end, I suddenly found myself with spare time on my hands for the first time since …, well, ever to be honest. I had no clear idea of what to do next and thought it might “serve the community well” to jot down a few thoughts on TTS. The initial idea was a slim “hardcore” technical book explaining the state of the art, but as writing continued I realised that more and more background material was needed. Eventually the initial idea was dropped and the more-comprehensive volume that you now see was written.
Some early notes were made in Edinburgh, but the book mainly started during a summer I spent in Boulder, Colorado. I was freelancing at that point but am grateful to Ron Cole and his group for accommodating me in such a friendly fashion. A good deal of work was completed outside the office and I am eternally grateful to Laura Michalis for putting me up, putting up with me and generally being there and supportive during that phase.
While the book was in effect written entirely by myself, I should pay particular thanks to Steve Young and Mark Gales as I used the HTK book and lecture notes directly in Chapter 15 and the appendix.
- Type
- Chapter
- Information
- Text-to-Speech Synthesis , pp. xxvii - xxviiiPublisher: Cambridge University PressPrint publication year: 2009