Within the context of robust acoustic features for automatic speech recognition (ASR), we evaluated mel-frequency cepstral coefficients (MFCCs) derived from two spectral representation techniques, i.e. the fast Fourier transform (FFT) and linear predictive coding (LPC). ASR systems based on the two feature types were tested on a digit recognition task using continuous density hidden Markov phone models. System performance was determined in clean acoustic conditions as well as in different simulations of adverse acoustic conditions. The LPC-based MFCCs outperformed their FFT counterparts in most of the adverse acoustic conditions that were investigated in this study. A tentative explanation for this difference in recognition performance is given.
Cite as: Wet, F.d., Cranen, B., Veth, J.d., Boves, L. (2001) A comparison of LPC and FFT-based acoustic features for noise robust ASR. Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001), 865-868, doi: 10.21437/Eurospeech.2001-264
@inproceedings{wet01_eurospeech,
author={Febe de Wet and Bert Cranen and Johan de Veth and Loe Boves},
title={{A comparison of LPC and FFT-based acoustic features for noise robust ASR}},
year=2001,
booktitle={Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001)},
pages={865--868},
doi={10.21437/Eurospeech.2001-264}
}