Kernel k-means and spectral clustering have been used to separate input space clusters by means of non-linear mappings. In this paper we adapt and extend these methods to identify constitutive units of speech: consonants, vowels and silences. The discover of this structure is very useful for prosody-based systems of automatic language identification or language disorders detection. In order to find stable speech segments, infra-phonetic segmentation is performed using the divergence forward-backward algorithm. Our test corpus is a six-languages subset of OGI_MLTS corpus. We present better classification results than traditional approaches as well as faster processing times.
Cite as: Arias, J.A. (2005) Unsupervised identification of speech segments using kernel methods for clustering. Proc. Interspeech 2005, 681-684, doi: 10.21437/Interspeech.2005-196
@inproceedings{arias05_interspeech,
author={José Anibal Arias},
title={{Unsupervised identification of speech segments using kernel methods for clustering}},
year=2005,
booktitle={Proc. Interspeech 2005},
pages={681--684},
doi={10.21437/Interspeech.2005-196}
}