August 3, 2006

Hierarchical Structures of Neural Networks for Phoneme Recognition

Key Points

Key points are not available for this paper at this time.

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.

Bookmark

Cite This Study

Schwarz et al. (Thu,) studied this question.

synapsesocial.com/papers/6a0ff4ee4fb650da4ffebc15 https://doi.org/https://doi.org/10.1109/icassp.2006.1660023

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Towards Lower Error Rates in Phoneme Recognition2004 · 104 citations
2Speaker-independent phone recognition using hidden Markov models1989 · 936 citations
3Connectionist Speech Recognition1994 · 580 citations
4Beyond a single critical-band in TRAP based ASR2003 · 28 citations
5Connectionist Speech Recognition: A Hybrid Approach1993 · 1,137 citations

Bookmark