The Philips Research System for Large-Vocabulary Continuous-Speech Recognition
V. Steinbiss, H. Ney, R. Haeb-Umbach, B.-H. Train, U. Essen, R. Kneser, M. Oerder, H.G. Meier, X. Aubert, C. Dugast, D. Geller, W. Hoellerbauer, H. Bartosik, in: EUROSPEECH, Berlin, 1993.
Conference Paper
| English
Author
Steinbiss, Volker;
Ney, Hermann;
Haeb-Umbach, ReinholdLibreCat;
Train, B.-H.;
Essen, U.;
Kneser, Reinhard;
Oerder, Martin;
Meier, H. G.;
Aubert, X.;
Dugast, Christian;
Geller, Dieter;
Hoellerbauer, W.
All
All
Abstract
This paper gives a status report of the Philips research system for phoneme-based, large-vocabulary, continuous-speech recognition. Like for many other systems, the recognition architecture is based on an integrated statistical approach. We describe the characteristic features of the system as opposed to other systems: 1. The Viterbi criterion is consistently applied both in training and testing. 2. Continuous mixture densities are used without tying or smoothing. 3. Time-synchronous beam search in connection with a phoneme look-ahead is applied to a tree-organized lexicon. The system has been successfully applied to the American English DARPA RM task. Here, we report experimental results for a German 13 000-word Philips internal dictation task. In addition to the scientific prototype, a PC version has been set up which is described here for the first time.
Publishing Year
Proceedings Title
EUROSPEECH, Berlin
LibreCat-ID
Cite this
Steinbiss V, Ney H, Haeb-Umbach R, et al. The Philips Research System for Large-Vocabulary Continuous-Speech Recognition. In: EUROSPEECH, Berlin. ; 1993.
Steinbiss, V., Ney, H., Haeb-Umbach, R., Train, B.-H., Essen, U., Kneser, R., … Bartosik, H. (1993). The Philips Research System for Large-Vocabulary Continuous-Speech Recognition. In EUROSPEECH, Berlin.
@inproceedings{Steinbiss_Ney_Haeb-Umbach_Train_Essen_Kneser_Oerder_Meier_Aubert_Dugast_et al._1993, title={The Philips Research System for Large-Vocabulary Continuous-Speech Recognition}, booktitle={EUROSPEECH, Berlin}, author={Steinbiss, Volker and Ney, Hermann and Haeb-Umbach, Reinhold and Train, B.-H. and Essen, U. and Kneser, Reinhard and Oerder, Martin and Meier, H. G. and Aubert, X. and Dugast, Christian and et al.}, year={1993} }
Steinbiss, Volker, Hermann Ney, Reinhold Haeb-Umbach, B.-H. Train, U. Essen, Reinhard Kneser, Martin Oerder, et al. “The Philips Research System for Large-Vocabulary Continuous-Speech Recognition.” In EUROSPEECH, Berlin, 1993.
V. Steinbiss et al., “The Philips Research System for Large-Vocabulary Continuous-Speech Recognition,” in EUROSPEECH, Berlin, 1993.
Steinbiss, Volker, et al. “The Philips Research System for Large-Vocabulary Continuous-Speech Recognition.” EUROSPEECH, Berlin, 1993.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Link(s) to Main File(s)
Access Level
Closed Access
Google Scholar