English

Phoneme recognition in TIMIT with BLSTM-CTC

Computation and Language 2008-04-22 v1 Neural and Evolutionary Computing

Abstract

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.

Keywords

Cite

@article{arxiv.0804.3269,
  title  = {Phoneme recognition in TIMIT with BLSTM-CTC},
  author = {Santiago Fernández and Alex Graves and Juergen Schmidhuber},
  journal= {arXiv preprint arXiv:0804.3269},
  year   = {2008}
}

Comments

8 pages

R2 v1 2026-06-21T10:33:02.239Z