Statistical Pronunciation Modeling for Non-Native Speech Processing

✍ Scribed by Rainer E. Gruhn, Wolfgang Minker, Satoshi Nakamura (auth.)

• Publisher: Springer-Verlag Berlin Heidelberg
• Year: 2011
• Tongue: English
• Leaves: 125
• Series: Signals and Communication Technology
• Edition: 1
• Category: Library

✦ Synopsis

In this work, the authors present a fully statistical approach to model non--native speakers' pronunciation. Second-language speakers pronounce words in multiple different ways compared to the native speakers. Those deviations, may it be phoneme substitutions, deletions or insertions, can be modelled automatically with the new method presented here.
The methods is based on a discrete hidden Markov model as a word pronunciation model, initialized on a standard pronunciation dictionary. The implementation and functionality of the methodology has been proven and verified with a test set of non-native English in the regarding accent.
The book is written for researchers with a professional interest in phonetics and automatic speech and speaker recognition.

✦ Table of Contents

Front Matter....Pages i-ix
Introduction....Pages 1-4
Automatic Speech Recognition....Pages 5-17
Properties of Non-native Speech....Pages 19-23
Pronunciation Variation Modeling in the Literature....Pages 25-30
Non-native Speech Database....Pages 31-46
Handling Non-native Speech....Pages 47-70
Pronunciation HMMs....Pages 71-83
Outlook....Pages 85-88
Back Matter....Pages 89-114

✦ Subjects

Signal, Image and Speech Processing; Language Translation and Linguistics; Phonology; Statistics for Engineering, Physics, Computer Science, Chemistry and Earth Sciences