Publication Details

Hierarchical structures of neural networks for phoneme recognition

SCHWARZ, P.; MATĚJKA, P.; ČERNOCKÝ, J. Hierarchical structures of neural networks for phoneme recognition. Proceedings of ICASSP 2006. Toulouse: 2006. p. 325-328.
Czech title
Hiearchické struktury neuronových sítí pro rozpoznávání fonémů
Type
conference paper
Language
English
Authors
Schwarz Petr, Ing., Ph.D. (DCGM)
Matějka Pavel, Ing., Ph.D. (DCGM)
Černocký Jan, prof. Dr. Ing. (DCGM)
URL
Keywords

phoneme recognition, neural networks, split temporal context, hierarchical neural networks, timit

Abstract

This paper deals with phoneme recognition based on neural networks(NN). The results of the final system reported on standard TIMIT databasecompare favorably to the best published results.

Annotation

This paper deals with phoneme recognition based on neural networks (NN). First,  several approaches to improve the phoneme error rate are suggested and discussed. In the experimental part, we concentrate on TempoRAl Patterns (TRAPs) and novel split temporal context (STC) phoneme recognizers. We also investigate into tandem NN architectures. The results of the final system reported on standard TIMIT database compare favorably to the best published results.

Published
2006
Pages
325–328
Proceedings
Proceedings of ICASSP 2006
Conference
International Conference on Acoustics, Speech, and Signal Processing , Toulouse,Francie, FR
Place
Toulouse
BibTeX 
@inproceedings{BUT22219,
  author="Petr {Schwarz} and Pavel {Matějka} and Jan {Černocký}",
  title="Hierarchical structures of neural networks for phoneme recognition",
  booktitle="Proceedings of ICASSP 2006",
  year="2006",
  pages="325--328",
  address="Toulouse",
  url="http://www.fit.vutbr.cz/~matejkap/publi/2006/ICASSP2006_Schwarz_PhnRec.pdf"
}
Back to top