| Paper: | SLP-P1.4 | ||
| Session: | Feature Extraction and Modeling | ||
| Time: | Tuesday, May 16, 10:30 - 12:30 | ||
| Presentation: | Poster | ||
| Topic: | Speech and Spoken Language Processing: Feature Extraction and Modeling | ||
| Title: | Hierarchical Structures of Neural Networks for Phoneme Recognition | ||
| Authors: | Petr Schwarz, Pavel Matejka, Jan Cernocky, Brno University of Technology, Czech Republic | ||
| Abstract: | 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. | ||
©2018 Conference Management Services, Inc. -||- email: webmaster@icassp2006.org -||- Last updated Friday, August 17, 2012