Robust Adaptation to Non-Native Accents in Automatic Speech Recognition
Authors: Goronzy, Silke
Buy this book
- About this book
-
Speech recognition technology is being increasingly employed in human-machine interfaces. A remaining problem however is the robustness of this technology to non-native accents, which still cause considerable difficulties for current systems.
In this book, methods to overcome this problem are described. A speaker adaptation algorithm that is capable of adapting to the current speaker with just a few words of speaker-specific data based on the MLLR principle is developed and combined with confidence measures that focus on phone durations as well as on acoustic features. Furthermore, a specific pronunciation modelling technique that allows the automatic derivation of non-native pronunciations without using non-native data is described and combined with the previous techniques to produce a robust adaptation to non-native accents in an automatic speech recognition system.
- Table of contents (13 chapters)
-
-
Introduction
Pages 1-5
-
ASR:AnOverview
Pages 7-13
-
Pre-processing of the Speech Data
Pages 15-19
-
Stochastic Modelling of Speech
Pages 21-29
-
Knowledge Bases of an ASR System
Pages 31-36
-
Table of contents (13 chapters)
- Download Sample pages 1 PDF (30.7 KB)
- Download Table of contents PDF (36.2 KB)
Recommended for you
Bibliographic Information
- Bibliographic Information
-
- Book Title
- Robust Adaptation to Non-Native Accents in Automatic Speech Recognition
- Authors
-
- Silke Goronzy
- Series Title
- Lecture Notes in Artificial Intelligence
- Series Volume
- 2560
- Copyright
- 2002
- Publisher
- Springer-Verlag Berlin Heidelberg
- Copyright Holder
- Springer-Verlag Berlin Heidelberg
- eBook ISBN
- 978-3-540-36290-6
- DOI
- 10.1007/3-540-36290-8
- Softcover ISBN
- 978-3-540-00325-0
- Edition Number
- 1
- Number of Pages
- XI, 146
- Topics
