Result Details
Hierarchical structures of neural networks for phoneme recognition
Matějka Pavel, Ing., Ph.D., DCGM (FIT)
Černocký Jan, prof. Dr. Ing., DCGM (FIT)
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.
phoneme recognition, neural networks, split temporal context, hierarchical neural networks, timit
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.
@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"
}
Centre of computer graphics, MŠMT, Centra základního výzkumu, LC06008, start: 2006-03-01, end: 2011-12-31, completed
New trends in research and application of voice technology, GACR, Standardní projekty, GA102/05/0278, start: 2005-01-01, end: 2007-12-31, completed