Spectral moments analysis has been shown to be effective in deriving acoustic features for classifying voiceless stop release bursts [1], and is an analysis method that has commonly been cited in the clinical phonetics literature dealing with children's disordered speech. In this study, we compared the classification of stops /p/, /t/, and /k/ based on spectral moments with classification based on an equal number of Bark Cepstrum coefficients. Utterance-initial /p/, /t/, and /k/ (1338 samples in all) were collected from a database of children's speech. Linear discriminant analysis (LDA) was used to classify the three stops based on four analysis frames from the initial 40 msec of each token. The best classification based on spectral moments used all four spectral moment features (computed from bark-scaled spectra) and all four time intervals and yielded 75.6% correct classification. The best classification based on Bark cepstrum yielded 83.4% correct also using four coefficients and four time frames.
Cite as: Bunnell, H.T., Polikoff, J., McNicholas, J. (2004) Spectral moment vs. bark cepstral analysis of children's word-initial voiceles stops. Proc. Interspeech 2004, 1313-1316, doi: 10.21437/Interspeech.2004-81
@inproceedings{bunnell04_interspeech,
author={H. Timothy Bunnell and James Polikoff and Jane McNicholas},
title={{Spectral moment vs. bark cepstral analysis of children's word-initial voiceles stops}},
year=2004,
booktitle={Proc. Interspeech 2004},
pages={1313--1316},
doi={10.21437/Interspeech.2004-81}
}