Convolutional Neural Networks for Phoneme Recognition

Cornelius Glackin, Julie Wall, Gérard Chollet, Nazim Dugan, Nigel Cannings

2018

Abstract

This paper presents a novel application of convolutional neural networks to phoneme recognition. The phonetic transcription of the TIMIT speech corpus is used to label spectrogram segments for training the convolutional neural network. A window of a fixed size slides over the spectrogram of the TIMIT utterances and the resulting spectrogram patches are assigned to the appropriate phone class by parsing TIMIT’s phone transcription. The convolutional neural network is the standard GoogLeNet implementation trained with stochastic gradient descent with mini batches. After training, phonetic rescoring is performed in the usual way to map the TIMIT phone set to the smaller standard set. Benchmark results are presented for comparison to other state-of-the-art approaches. Finally, conclusions and future directions with regard to extending the approach are discussed.

Download


Paper Citation


in Harvard Style

Glackin C., Wall J., Chollet G., Dugan N. and Cannings N. (2018). Convolutional Neural Networks for Phoneme Recognition.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 190-195. DOI: 10.5220/0006653001900195


in Bibtex Style

@conference{icpram18,
author={Cornelius Glackin and Julie Wall and Gérard Chollet and Nazim Dugan and Nigel Cannings},
title={Convolutional Neural Networks for Phoneme Recognition},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={190-195},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006653001900195},
isbn={978-989-758-276-9},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Convolutional Neural Networks for Phoneme Recognition
SN - 978-989-758-276-9
AU - Glackin C.
AU - Wall J.
AU - Chollet G.
AU - Dugan N.
AU - Cannings N.
PY - 2018
SP - 190
EP - 195
DO - 10.5220/0006653001900195