In this paper we describe the optimization of 'conventional template matching techniques for connected digit recognition (TI/NIST connected digit corpus). In particular we carried out a series of experiments in which we studied various aspects of signal processing, acoustic modeling, mixture densities and linear transforms of the acoustic vector. After all optimization steps, our best string error rate on the TI/NIST connected digit corpus was 1.71% for single densities and 0.74% for mixture densities.
Cite as: Welling, L., Ney, H., Eiden, A., Forbrig, C. (1995) Connected digit recognition using statistical template matching. Proc. 4th European Conference on Speech Communication and Technology (Eurospeech 1995), 1483-1486, doi: 10.21437/Eurospeech.1995-363
@inproceedings{welling95_eurospeech,
author={L. Welling and Hermann Ney and A. Eiden and C. Forbrig},
title={{Connected digit recognition using statistical template matching}},
year=1995,
booktitle={Proc. 4th European Conference on Speech Communication and Technology (Eurospeech 1995)},
pages={1483--1486},
doi={10.21437/Eurospeech.1995-363}
}