Robust Entropy-based Endpoint Detection for Speech Recognition in Noisy Environments
Journal
5th International Conference on Spoken Language Processing, ICSLP 1998
Date Issued
1998
Author(s)
Abstract
This paper presents an entropy-based algorithm for accurate and robust endpoint detection for speech recognition under noisy environments. Instead of using the conventional energy-based features, the spectral entropy is developed to identify the speech segments accurately. Experimental results show that this algorithm outperforms the energy-based algorithms in both detection accuracy and recognition performance under noisy environments, with an average error rate reduction of more than 16%. © 1998. 5th International Conference on Spoken Language Processing, ICSLP 1998. All rights reserved.
Other Subjects
Entropy; Detection accuracy; End point detection; Energy-based; Energy-based algorithms; Entropy-based; Entropy-based algorithm; Noisy environment; Performance; Spectral entropy; Speech segments; Speech recognition
Type
conference paper