Publication Details

Cross-Domain and Cross-Language Portability of Acoustic Features Estimated by Multilayer Perceptrons

STOLCKE Andreas, GRÉZL František, HWANG Mei-Yuh, LEI Xin, MORGAN Nelson and VERGYRI Dimitra. Cross-Domain and Cross-Language Portability of Acoustic Features Estimated by Multilayer Perceptrons. In: 2006 IEEE International Conference on Acoustic, Speech, and Signal Processing. Toulouse: IEEE Signal Processing Society, 2006, pp. 321-324. ISBN 978-3-540-74627-0.
Type
conference paper
Language
english
Authors
Stolcke Andreas (SRI)
Grézl František, Ing., Ph.D. (DCGM FIT BUT)
Hwang Mei-Yuh (UWASH)
Lei Xin (UWASH)
Morgan Nelson, Prof. (ICSI Berkeley)
Vergyri Dimitra (UC Berkeley)
Keywords

Cross domains, cross language, portability, probabilistic features, MLP features

Abstract

Cross domains and language portability of phone-posterior features. English-trained MLP features can provide a significant
boost to recognition accuracy in new domains within the same
language, as well as in entirely different languages such as Mandarin and Arabic.

Annotation

Recent results with phone-posterior acoustic features estimated by
multilayer perceptrons (MLPs) have shown that such features can
effectively improve the accuracy of state-of-the-art large vocabulary
speech recognition systems. MLP features are trained discriminatively
to perform phone classification and are therefore,
like acoustic models, tuned to a particular language and application
domain. In this paper we investigate how portable such features
are across domains and languages. We show that even without
retraining, English-trainedMLP features can provide a significant
boost to recognition accuracy in new domainswithin the same
language, as well as in entirely different languages such as Mandarin
and Arabic. We also show the effectiveness of feature-level
adaptation in porting MLP features to new domains.

Published
2006
Pages
321-324
Proceedings
2006 IEEE International Conference on Acoustic, Speech, and Signal Processing
Conference
International Conference on Acoustics, Speech, and Signal Processing , Toulouse,Francie, FR
ISBN
978-3-540-74627-0
Publisher
IEEE Signal Processing Society
Place
Toulouse, FR
BibTeX
@INPROCEEDINGS{FITPUB8248,
   author = "Andreas Stolcke and Franti\v{s}ek Gr\'{e}zl and Mei-Yuh Hwang and Xin Lei and Nelson Morgan and Dimitra Vergyri",
   title = "Cross-Domain and Cross-Language Portability of Acoustic Features Estimated by Multilayer Perceptrons",
   pages = "321--324",
   booktitle = "2006 IEEE International Conference on Acoustic, Speech, and Signal Processing",
   year = 2006,
   location = "Toulouse, FR",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-3-540-74627-0",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/8248"
}
Back to top