Framewise phoneme classification with bidirectional LSTM networks

  title={Framewise phoneme classification with bidirectional LSTM networks},
  author={Alex Graves and Juergen Schmidhuber},
  journal={Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.},
  pages={2047-2052 vol. 4}
In this paper, we apply bidirectional training to a long short term memory (LSTM) network for the first time. We also present a modified, full gradient version of the LSTM learning algorithm. We discuss the significance of framewise phoneme classification to continuous speech recognition, and the validity of using bidirectional networks for online causal tasks. On the TIMIT speech database, we measure the framewise phoneme classification scores of bidirectional and unidirectional variants of… CONTINUE READING
Highly Influential
This paper has highly influenced 11 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 190 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 116 extracted citations

Cambricon: An Instruction Set Architecture for Neural Networks

2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) • 2016
View 5 Excerpts
Highly Influenced

Chinese-thai cross-language topic extraction and alignment

2017 International Conference on Asian Language Processing (IALP) • 2017
View 10 Excerpts
Highly Influenced

190 Citations

Citations per Year
Semantic Scholar estimates that this publication has 190 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 23 references

On supervised learning from sequential data with applications for speech recognition

M. Schuster
PhD thesis, Nara Institute of Science and Technolog, • 1999
View 4 Excerpts
Highly Influenced

A new approach to continuous speech recognition using LSTM recurrent neural networks

D. Eck, A. Graves, J. Schmidhuber
Technical Report IDSIA-14-03, • 2003
View 1 Excerpt

Similar Papers

Loading similar papers…