Title :
The RWTH large vocabulary continuous speech recognition system
Author :
Ney, H. ; Welling, L. ; Ortmanns, S. ; Beulen, K. ; Wessel, F.
Author_Institution :
Lehrstuhl fur Inf. VI, Tech. Hochschule Aachen, Germany
Abstract :
We present an overview of the RWTH Aachen large vocabulary continuous speech recognizer. The recognizer is based on continuous density hidden Markov models and a time-synchronous left-to-right beam search strategy. Experimental results on the ARPA Wall Street Journal (WSJ) corpus verify the effects of several system components, namely linear discriminant analysis, vocal tract normalization, pronunciation lexicon and cross-word triphones, on the recognition performance
Keywords :
acoustic signal processing; hidden Markov models; search problems; speech recognition; ARPA Wall Street Journal corpus; Aachen; RWTH speech recognition system; acoustic front-end; acoustic modelling; continuous density hidden Markov models; cross-word triphones; decision-tree based state tying; experimental results; large vocabulary continuous speech recognition; linear discriminant analysis; maximum likelihood training; pronunciation lexicon; recognition performance; time-synchronous left-to-right beam search; vocal tract normalization; Acoustic beams; Acoustic emission; Cepstrum; Filters; Hidden Markov models; Linear discriminant analysis; Loudspeakers; Speech recognition; Vectors; Vocabulary;
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4428-6
DOI :
10.1109/ICASSP.1998.675399
