Long-Term Spectral Pseudo-Entropy (LTSPE) Feature

This is the source code (MATLAB) of the LTSPE feature.


Speech detection systems are known as a type of audio classifier systems which are used to recognize, detect or mark parts of audio signal including human speech. Here, a novel robust feature named Long-Term Spectral Pseudo-Entropy (LTSPE) is proposed to detect speech and its purpose is to improve performance in combination with other features, increase accuracy and to have acceptable performance. Experimental results show that if LTSPE is combined with other features, performance of the detector is improved. Moreover, this feature has higher accuracy compared to similar ones.

Submit an Analysis

Dataset Files

No Data files have been uploaded.

OPEN ACCESS Dataset Details

Citation Author(s):
mohammad rasoul kahrizi
Submitted by:
mohammad rasoul...
Last updated:
Fri, 12/01/2017 - 08:44
Data Format:


[1] mohammad rasoul kahrizi, "Long-Term Spectral Pseudo-Entropy (LTSPE) Feature", IEEE Dataport, 2017. [Online]. Available: http://dx.doi.org/10.21227/H2G05K. Accessed: Dec. 11, 2017.
doi = {10.21227/H2G05K},
url = {http://dx.doi.org/10.21227/H2G05K},
author = {mohammad rasoul kahrizi },
publisher = {IEEE Dataport},
title = {Long-Term Spectral Pseudo-Entropy (LTSPE) Feature},
year = {2017} }
T1 - Long-Term Spectral Pseudo-Entropy (LTSPE) Feature
AU - mohammad rasoul kahrizi
PY - 2017
PB - IEEE Dataport
UR - 10.21227/H2G05K
ER -
mohammad rasoul kahrizi. (2017). Long-Term Spectral Pseudo-Entropy (LTSPE) Feature. IEEE Dataport. http://dx.doi.org/10.21227/H2G05K
mohammad rasoul kahrizi, 2017. Long-Term Spectral Pseudo-Entropy (LTSPE) Feature. Available at: http://dx.doi.org/10.21227/H2G05K.
mohammad rasoul kahrizi. (2017). "Long-Term Spectral Pseudo-Entropy (LTSPE) Feature." Web.
1. mohammad rasoul kahrizi. Long-Term Spectral Pseudo-Entropy (LTSPE) Feature [Internet]. IEEE Dataport; 2017. Available from : http://dx.doi.org/10.21227/H2G05K
mohammad rasoul kahrizi. "Long-Term Spectral Pseudo-Entropy (LTSPE) Feature." doi: 10.21227/H2G05K