Phoneme recognition in TIMIT with BLSTM-CTC

Santiago Fern\'andez, Alex Graves, Juergen Schmidhuber
Arxiv ID: 804.3269Last updated: 4/22/2008
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.

PaperStudio AI Chat

I'm your research assistant! Ask me anything about this paper.

Related papers

Commercial Disclosure
© 2023 Paper Studio™. All Rights Reserved.