Deep Learning of Speech Features for Improved Phonetic Recognition

Abstract

Recently, a remarkable performance result of 23.0% Phone Error Rate (PER) on the TIMIT core test set was reported by applying Deep Belief Network (DBN) on phonetic recognition [1]. Despite the good performance reported, there is still substantial room for improvement in the reported design in order to achieve optimal results. In this letter, we present an… (More)

Topics

6 Figures and Tables

Cite this paper

@inproceedings{Lee2011DeepLO, title={Deep Learning of Speech Features for Improved Phonetic Recognition}, author={Jaehyung Lee and Soo Young Lee}, booktitle={INTERSPEECH}, year={2011} }