This paper proposes acoustic-phonetic features for classification of place-of-articulation of stop consonants derived from their temporal structures. The speech signal corresponding to a stop is characterized by several temporal features such as sub-band zero-crossings and envelope fits. Classification experiments on the stops from the TIMIT (read speech) and the Buckeye (conversational speech) databases using a support vector machine classifier demonstrate that the performance of the proposed features (84.6%) is comparable to that obtained by MFCCs (85.1%) in many aspects. Further, the classification accuracy is boosted (90.1%) with the combination of temporal and MFCC features, which substantiates their supplementary nature.
Cite as: Prathosh, A.P., Ramakrishnan, A.G., Ananthapadmanabha, T.V. (2015) Classification of place-of-articulation of stop consonants using temporal analysis. Proc. Interspeech 2015, 2655-2659, doi: 10.21437/Interspeech.2015-397
@inproceedings{prathosh15_interspeech,
author={A. P. Prathosh and A. G. Ramakrishnan and T. V. Ananthapadmanabha},
title={{Classification of place-of-articulation of stop consonants using temporal analysis}},
year=2015,
booktitle={Proc. Interspeech 2015},
pages={2655--2659},
doi={10.21437/Interspeech.2015-397}
}