Phoneme recognition in TIMIT with BLSTM-CTC

2008/04/21 by Fernández, Santiago, Graves, Alex, Schmidhuber, Juergen
#Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.7 #I.5.4 #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.0804.3269

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.

Related

• A Survey of Recent DNN Architectures on the TIMIT Phone Recognition Task
• A Comparison of Adaptation Techniques and Recurrent Neural Network Architectures
• Recurrent DNNs and its Ensembles on the TIMIT Phone Recognition Task
• End-to-end Phoneme Sequence Recognition using Convolutional Neural\n Networks
• Application of Word2vec in Phoneme Recognition