In speech recognition suitable feature extraction is an important issue. In our research we tested the performance of several individual feature vectors, as well as various combinations of these vectors. As a basis for the feature vectors we use two types of analysis: a 15-band filterbank and an LPC-cepstral analysis. From these base-feature vectors several other feature vectors are derived. In the recognition part of our system (REXY) we used HMM's to model phone-like-units (PLU's). The system is trained on continuous speech of one male speaker. We tested the different feature vectors separately, and some of their combinations (combining feature vectors is done at a probabilistic level). The overall performance of the filterbank analysis turns out to be better than the LPC-cepstral analysis. keywords; speech recognition, HMM, feature vectors.
Cite as: Alphen, P.v., Pols, L.C.W. (1991) Comparing various feature vectors in automatic speech recognition. Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991), 533-536, doi: 10.21437/Eurospeech.1991-133
@inproceedings{alphen91_eurospeech,
author={Paul van Alphen and Louis C. W. Pols},
title={{Comparing various feature vectors in automatic speech recognition}},
year=1991,
booktitle={Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991)},
pages={533--536},
doi={10.21437/Eurospeech.1991-133}
}