BROADCAST NEWS PHONEME RECOGNITION BY SPARSE CODING

Joseph Razik, Sébastien Paris, Hervé Glotin

2012

Abstract

We present in this paper a novel approach for the phoneme recognition task that we want to extend to an automatic speech recognition system (ASR). Usual ASR systems are based on a GMM-HMM combination that represents a fully generative approach. Current discriminative methods are not tractable in large scale data set case, especially with non-linear kernel. In our system, we introduce a new scheme using jointly sparse coding and an approximation additive kernel for fast SVM training for phoneme recognition. Thus, on a broadcast news corpus, our system outperforms the use of GMMs by around 2.5% and is computationally linear to the number of samples.

Paper Citation

in Harvard Style

Razik J., Paris S. and Glotin H. (2012). BROADCAST NEWS PHONEME RECOGNITION BY SPARSE CODING . In Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM, ISBN 978-989-8425-99-7, pages 191-197. DOI: 10.5220/0003778201910197

in Bibtex Style

@conference{icpram12,
author={Joseph Razik and Sébastien Paris and Hervé Glotin},
title={BROADCAST NEWS PHONEME RECOGNITION BY SPARSE CODING},
booktitle={Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,},
year={2012},
pages={191-197},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003778201910197},
isbn={978-989-8425-99-7},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 2: ICPRAM,
TI - BROADCAST NEWS PHONEME RECOGNITION BY SPARSE CODING
SN - 978-989-8425-99-7
AU - Razik J.
AU - Paris S.
AU - Glotin H.
PY - 2012
SP - 191
EP - 197
DO - 10.5220/0003778201910197