Third European Conference on Speech Communication and Technology

Berlin, Germany
September 22-25, 1993


Evaluation of an HMM Speech Recognizer With Various Continuous Speech Databases

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

Daimler Benz AG, Research Institute, Ulm, Germany

This paper describes a speaker-independent HMM continuous speech recognizer and its evaluation with three large continuous speech databases recorded at several German universities and industrial sites. These databases differ with regard to recording conditions, speaking rate, microphone location, amount of training and test data, and application dependency of the training material. The recognition system is based on mel-cepstral coefficients, a linear discriminant transform of cepstral data, a soft-decision vector quantizer with gaussian distributions, and semi-continuous Hidden Markov Models (SCHMM) of context-dependent subword units.

Keywords: Continuous speech recognition, linear discriminant analysis, SCHMM, speech databases, word graphs.

Full Paper

Bibliographic reference.  Class, F. / Kaltenmeier, A. / Regel-Brietzmann, Peter (1993): "Evaluation of an HMM speech recognizer with various continuous speech databases", In EUROSPEECH'93, 1587-1590.