ISCA Archive Eurospeech 1993
ISCA Archive Eurospeech 1993

The Philips research system for large-vocabulary continuous-speech recognition

Volker Steinbiss, Hermann Ney, Reinhold Haeb-Umbach, B.-H. Iran, U. Essen, Reinhard Kneser, M. Oerder, H.-G. Meier, X. Aubert, Christian Dugast, D. Geller, W. Hollerbauer, H. Bartosik

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.

Keywords: Continuous speech recognition, large vocabulary recognition