An improved speech detection algorithm for isolated Korean utterances
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
Automatic silence/unvoiced/voiced classification of speech using a modified Teager energy feature
CONTROL'05 Proceedings of the 2005 WSEAS international conference on Dynamical systems and control
Artificial Intelligence in Medicine
Voice activity detection using generalized gamma distribution
SETN'06 Proceedings of the 4th Helenic conference on Advances in Artificial Intelligence
IWANN'05 Proceedings of the 8th international conference on Artificial Neural Networks: computational Intelligence and Bioinspired Systems
Score function for voice activity detection
NOLISP'09 Proceedings of the 2009 international conference on Advances in Nonlinear Speech Processing
Hi-index | 0.00 |
Zero crossing rate and energy of the speech signal have been the two most widely used features for locating the endpoints of an utterance. We propose a new energy measure, based on Teager's energy algorithm. This new energy measure simplifies the process of endpoint detection. We present examples showing that the new measure is more effective than traditional measures in capturing some speech events, and present experimental results demonstrating that the measure can be used to improve the performance of endpoint detection algorithms.