We are going to refer to the problem of speech recognition under noisy conditions, with medium size vocabularies of isolated words. We describe a method for feature extraction and the scores obtained with a HMM based recognizer. This method uses a combination of others two methods: the Short-time Modified Coherence and the spectral subtraction.
Cite as: Gomez-Mena, J., Santos-Suarez, J., Garcia-Gomez, R. (1991) A robust feature extraction method for automatic speech recognition in noisy environments. Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991), 1383-1386, doi: 10.21437/Eurospeech.1991-316
@inproceedings{gomezmena91_eurospeech,
author={Juan Gomez-Mena and J. Santos-Suarez and Ramón Garcia-Gomez},
title={{A robust feature extraction method for automatic speech recognition in noisy environments}},
year=1991,
booktitle={Proc. 2nd European Conference on Speech Communication and Technology (Eurospeech 1991)},
pages={1383--1386},
doi={10.21437/Eurospeech.1991-316}
}