International Symposium on Chinese Spoken Language Processing (ISCSLP 2002)

Taipei, Taiwan
August 23-24, 2002

An Improved Entropy-based Endpoint Detection Algorithm

Chuan JIA, Bo XU

Chinese Academy of Sciences, Beijing, China

It is found that the detection using basic spectral entropy becomes difficult and inaccurate when speech signals are contaminated by high noise. This paper presents an improved entropy-based algorithm. The way to compute spectral probability density function of entropy is altered by the introduction of a positive constant. The modification improves the discriminability between speech and noise and the robustness of entropy so that it becomes easier to set thresholds. Experiment results reveal the validity of the improved entropy and prove that the improved entropy outperforms basic entropy. Moreover, the improvement of accurate rate (5db SNR) reaches 12.9% for the detection of start and end points averagely comparing with a pure energy-based algorithm.

Full Paper

Bibliographic reference.  JIA, Chuan / XU, Bo (2002): "An improved entropy-based endpoint detection algorithm", In ISCSLP 2002, paper 96.