Third European Conference on Speech Communication and Technology

Berlin, Germany
September 22-25, 1993


Optimization of an HMM - Based Continuous Speech Recognizer

F. Class, A. Kaltenmeier, Peter Regel-Brietzmann

Daimler-Benz AG, Research Institute, Ulm, Germany

This paper describes some optimizations to our speech recognition system, which is based on semi-continuous Hidden Markov Models (SCHMM) of subword units. The optimizations pertain to codebook generation, Linear Discriminant Analysis (LDA), initialized training, and definition of subword units. The recognition rate of the continuous version of the system increased from 79% to 95% combining all of the optimization steps.

Keywords: SCHMM, LDA, continuous speech recognition, codebook generation, sub-word units

Full Paper

Bibliographic reference.  Class, F. / Kaltenmeier, A. / Regel-Brietzmann, Peter (1993): "Optimization of an HMM - based continuous speech recognizer", In EUROSPEECH'93, 803-806.