Phoneme recognition in TIMIT with BLSTM-CTC

Simple item page
dc.creatorFernández, Santiago
dc.creatorGraves, Alex
dc.creatorSchmidhuber, Juergen
dc.date2008-04-21
dc.date.accessioned2026-07-07T09:33:44Z
dc.date.available2026-07-07T09:33:44Z
dc.descriptionWe 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.
dc.description8 pages
dc.identifierhttps://arxiv.org/abs/0804.3269
dc.identifierhttp://arxiv.org/abs/0804.3269
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/159241
dc.subjectComputation and Language
dc.subjectNeural and Evolutionary Computing
dc.subjectI.2.7; I.5.4
dc.titlePhoneme recognition in TIMIT with BLSTM-CTC
dc.typetext

Files

Collections

arXiv