Robust Adaptation to Non-Native Accents in Automatic Speech Recognition / by Silke Goronzy.

Format:

Book

Author/Creator:

Goronzy, Silke, author.

Contributor:

SpringerLink (Online service)

Series:

Computer Science (Springer-11645)

Lecture notes in computer science. Lecture notes in artificial intelligence ; 2560.

Lecture Notes in Artificial Intelligence ; 2560

Language:

English

Subjects (All):

Artificial intelligence.

Signal processing.

Image processing.

Speech processing systems.

Logic, Symbolic and mathematical.

User interfaces (Computer systems).

Artificial Intelligence.

Signal, Image and Speech Processing.

Mathematical Logic and Formal Languages.

User Interfaces and Human Computer Interaction.

Local Subjects:

Artificial Intelligence.

Signal, Image and Speech Processing.

Mathematical Logic and Formal Languages.

User Interfaces and Human Computer Interaction.

Physical Description:

1 online resource (XI, 146 pages).

Edition:

First edition 2002.

Contained In:

Springer eBooks

Place of Publication:

Berlin, Heidelberg : Springer Berlin Heidelberg : Imprint: Springer, 2002.

System Details:

text file PDF

Summary:

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.

Contents:

ASR:AnOverview

Pre-processing of the Speech Data

Stochastic Modelling of Speech

Knowledge Bases of an ASR System

Speaker Adaptation

Confidence Measures

Pronunciation Adaptation

Future Work

Summary

Databases and Experimental Settings

MLLR Results

Phoneme Inventory.

Other Format:

Printed edition:

ISBN:

978-3-540-36290-6

9783540362906

Access Restriction:

Restricted for use by site license.