Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System

R. Haeb-Umbach, X.L. Aubert, P. Beyerlein, D. Klakow, M. Ullrich, A. Wendemuth, P. Wilcox, in: DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne, 1998.

Conference Paper | English
Author
; ; ; ; ; ;
Abstract
In this paper we describe some characteristics of the acoustic modeling used in the Philips continuous-speech recognition system for the DARPA Hub-4 1997 evaluation, which are related to robustness issues. We aimed at a conceptually simple system: We trained two model sets on 70 hours of the Hub-4 training data, one for within-word and one for cross-word decoding. These model sets were used for both genders and all environmental conditions. In order to be able to do so, channel normalization (mean, variance normalization) and speaker normalization (vocal tract length normalization, realized by an appropriate shift of the center frequencies of the mel filter bank) have been applied, as well as adaptation techniques. MLLR-based unsupervised batch adaptation on clusters of segments was conducted both after a first within-word decoding and a cross-word decoding pass. The training strategy and the effects of the various normalization and adaptation techniques will be discussed in the paper.
Publishing Year
Proceedings Title
DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne
LibreCat-ID

Cite this

Haeb-Umbach R, Aubert XL, Beyerlein P, et al. Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System. In: DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne. ; 1998.
Haeb-Umbach, R., Aubert, X. L., Beyerlein, P., Klakow, D., Ullrich, M., Wendemuth, A., & Wilcox, P. (1998). Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System. In DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne.
@inproceedings{Haeb-Umbach_Aubert_Beyerlein_Klakow_Ullrich_Wendemuth_Wilcox_1998, title={Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System}, booktitle={DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne}, author={Haeb-Umbach, Reinhold and Aubert, Xavier L. and Beyerlein, Peter and Klakow, Dietrich and Ullrich, Meinhard and Wendemuth, Andreas and Wilcox, Patricia}, year={1998} }
Haeb-Umbach, Reinhold, Xavier L. Aubert, Peter Beyerlein, Dietrich Klakow, Meinhard Ullrich, Andreas Wendemuth, and Patricia Wilcox. “Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System.” In DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne, 1998.
R. Haeb-Umbach et al., “Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System,” in DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne, 1998.
Haeb-Umbach, Reinhold, et al. “Acoustic Modeling in the Philips Hub-4 Continuous-Speech Recognition System.” DARPA Broadcast News Transcription and Understanding Workshop, Landsdowne, 1998.

Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar