Text-to-Speech Synthesis 1st Edition

Totally excellent. Well-written. Clear. Comprehensive. Easy to read. Starts from fundamentals, and builds up. Just in case you don't have a background in signal processing and z-transforms, the author takes two semesters of electrical engineering and compresses them into chapter 10. Goes on to cover acoustics, MFCC, PSOLA, HMMs, unit selection, prosody and intonation, system architectures, etc. This is a solid graduate-level or advanced undergraduate textbook. It gives a comprehensive, in-depth overview coverage of the state of the art in TTS best practices as of 2009. It should become the standard go-to graduate textbook in this field for the next 10 years.Errata: many magnitude plots are labeled log magnitude, eg p.344,345. Log magnitude labeled amplitude, p.354. P306(d) and probably (c) and (e), y axis is way off, should start around 0 at the top and go down. Log(0) is -infinity, clips at bottom of graph, but here it got bumped up so log(0) is 0 on the y axis. (C) and (d) should add to (e), but we have no idea what's going on with the y axes being pulled out of a hat. P369 eq 12.40 should be ak-i not -1. P334 fig1.16(b) is missing a join to the single output.Apart from these typos it's still a 5 star book.

I have found myself turning to this book quite often as I work on various projects. I'm glad I bought it and recommend it to others.

Everything went very smooth.

I work at a small company doing text to speech. This book explains all aspects better than I could.

This book is an excellent introduction to all aspects of speech synthesis. It tells you everything you need to know, with ample discussion as to why you need to know it. There's also plenty of material suitable for readers already familiar with the subject who are interested in more advanced discussions. The discussion of HMM-based synthesis is a good example of this - the text is a good accompaniment to the current literature. There's also a very good introduction to speech signal processing, particularly for students with a good math background but who haven't yet studied DSP.This book is one of the core texts for the Cambridge MPhil in Computer Speech, Text and Internet Technology. By all accounts, students have found the material very helpful and interesting. I recommend it highly.

This was my first book on TTS, and I couldn't be happier with it. It makes me want to study the field further, in that it was presented in a way that was easy to understand for someone with little or no previous knowledge about TTS. I would highly recommend it.