Phoneme recognition in TIMIT with BLSTM-CTC

Thumbnail Image

Date

Authors

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Description

We compare the performance of a recurrent neural network with the best results published so far on phoneme recognition in the TIMIT database. These published results have been obtained with a combination of classifiers. However, in this paper we apply a single recurrent neural network to the same task. Our recurrent neural network attains an error rate of 24.6%. This result is not significantly different from that obtained by the other best methods, but they rely on a combination of classifiers for achieving comparable performance.
8 pages

Keywords

Computation and Language, Neural and Evolutionary Computing, I.2.7; I.5.4

Citation

URI

http://salesiana.dossiersoluciones.com/handle/123456789/159241

Consulte el texto completo en el siguiente enlace:

https://arxiv.org/abs/0804.3269
 http://arxiv.org/abs/0804.3269

Collections

arXiv