Shen J.-LHung J.-WLIN-SHAN LEE2023-06-092023-06-091998https://www.scopus.com/inward/record.uri?eid=2-s2.0-77951493947&partnerID=40&md5=e08c9e95da495acdf329e94404efc684https://scholars.lib.ntu.edu.tw/handle/123456789/632415This 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.Entropy; Detection accuracy; End point detection; Energy-based; Energy-based algorithms; Entropy-based; Entropy-based algorithm; Noisy environment; Performance; Spectral entropy; Speech segments; Speech recognitionconference paper2-s2.0-77951493947