Text-to-Speech Synthesis

Paul Taylor received his PhD from the University of Edinburgh, and is the founder and Chief Executive Officer of Phonetic Arts Ltd. He has previously been Lecturer and Director in the Centre for Speech Technology Research at the University of Edinburgh, a visiting lecturer at the University of Cambridge, and was founder and Chief Technical Officer of Rhetorical Systems.

• 1. Introduction; 2. Communication and language; 3. The text-to-speech problem; 4. Text segmentation and organisation; 5. Text decoding; 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. Conclusions.

'According to Taylor, 'in written language the author may take the liberty of explaining something in a complicated fashion knowing that the reader can go back and read this several times'. However, this is not true in the case of his book. Taylor so clearly presents the concepts, that re-reading is unnecessary.' Joao Luis G. Rosa, Computing Reviews