PRIZES to win! PROMOTIONS

Close Notification

Your cart does not contain any items

Robust Adaptation to Non-Native Accents in Automatic Speech Recognition

Silke Goronzy

$126.95   $101.37

Paperback

Not in-store but you can order this
How long will it take?

QTY:

English
Springer-Verlag Berlin and Heidelberg GmbH & Co. K
19 December 2002
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.
By:  
Imprint:   Springer-Verlag Berlin and Heidelberg GmbH & Co. K
Country of Publication:   Germany
Edition:   2002 ed.
Volume:   2560
Dimensions:   Height: 235mm,  Width: 155mm,  Spine: 8mm
Weight:   530g
ISBN:   9783540003250
ISBN 10:   3540003258
Series:   Lecture Notes in Computer Science
Pages:   146
Publication Date:  
Audience:   College/higher education ,  Professional and scholarly ,  Further / Higher Education ,  Undergraduate
Format:   Paperback
Publisher's Status:   Active
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.

See Also