Publication Details
Cross-Domain and Cross-Language Portability of Acoustic Features Estimated by Multilayer Perceptrons
Grézl František, Ing., Ph.D. (DCGM)
Hwang Mei-Yuh
Lei Xin
Morgan Nelson, prof.
Vergyri Dimitra
Cross domains, cross language, portability, probabilistic features, MLP features
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.
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.
@inproceedings{BUT22432,
author="Andreas {Stolcke} and František {Grézl} 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",
booktitle="2006 IEEE International Conference on Acoustic, Speech, and Signal Processing",
year="2006",
pages="321--324",
publisher="IEEE Signal Processing Society",
address="Toulouse",
isbn="978-3-540-74627-0"
}