E-Book, Englisch, 196 Seiten
Sakti / Markov / Nakamura Incorporating Knowledge Sources into Statistical Speech Recognition
1. Auflage 2009
ISBN: 978-0-387-85830-2
Verlag: Springer-Verlag
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)
E-Book, Englisch, 196 Seiten
ISBN: 978-0-387-85830-2
Verlag: Springer-Verlag
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)
Incorporating Knowledge Sources into Statistical Speech Recognition addresses the problem of developing efficient automatic speech recognition (ASR) systems, which maintain a balance between utilizing a wide knowledge of speech variability, while keeping the training / recognition effort feasible and improving speech recognition performance. The book provides an efficient general framework to incorporate additional knowledge sources into state-of-the-art statistical ASR systems. It can be applied to many existing ASR problems with their respective model-based likelihood functions in flexible ways.
Autoren/Hrsg.
Weitere Infos & Material
1;Preface;7
2;Contents;9
3;List of Figures;12
4;List of T ables;18
5;Glossary;19
6;1 Introduction and Book Overview;22
7;2 Statistical Speech Recognition;39
8;3 Graphical Framework to Incorporate Knowledge Sources;74
9;4 Speech Recognition Using GFIKS;97
10;5 Conclusions and Future Directions;156
11;A Speech Materials;161
12;B ATR Software Tools;168
13;C Composition of Bayesian Wide-phonetic Context;177
14;D Statistical Signicance Testing;182
15;References;188
16;Index;201
