Overview
- Presents a new methodology for speech recognition of non-native speakers
- Shows a proven and verified approach
- Includes supplementary material: sn.pub/extras
Part of the book series: Signals and Communication Technology (SCT)
Access this book
Tax calculation will be finalised at checkout
Other ways to access
Table of contents (8 chapters)
About this book
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.
Authors and Affiliations
Bibliographic Information
Book Title: Statistical Pronunciation Modeling for Non-Native Speech Processing
Authors: Rainer E. Gruhn, Wolfgang Minker, Satoshi Nakamura
Series Title: Signals and Communication Technology
DOI: https://doi.org/10.1007/978-3-642-19586-0
Publisher: Springer Berlin, Heidelberg
eBook Packages: Engineering, Engineering (R0)
Copyright Information: Springer-Verlag Berlin Heidelberg 2011
Hardcover ISBN: 978-3-642-19585-3Published: 08 May 2011
Softcover ISBN: 978-3-642-26814-4Published: 15 July 2013
eBook ISBN: 978-3-642-19586-0Published: 08 May 2011
Series ISSN: 1860-4862
Series E-ISSN: 1860-4870
Edition Number: 1
Number of Pages: X, 114
Topics: Signal, Image and Speech Processing, Natural Language Processing (NLP), Phonology and Phonetics, Statistics for Engineering, Physics, Computer Science, Chemistry and Earth Sciences