By analyzing the features of the audio signal,and solving the problem of confused recognition between pure music and speech sounds-music mixed part,a method which can recognize pure music and speech sounds-music mixed part,based on the average short time energy and standard deviation of zero-crossing rate features is put forward.

In this paper, EPD methods are reviewed based on short time average energy, short time average magnitude, short time average zero-crossing rate, dual-thresholds for short time average energy and short time average zero-crossing rate, cepstrum, entropy and also summarize methods on speech de-noising using wavelets firstly.

Adaptive algorithm of echo hiding based on short-time energy computing;

Aiming at low reliability in short-time energy analysis method for on-line monitoring of circuit breaker mechanical state, the paper studies the method to eliminate interference noise by using trip coil current signal to improve the reliability of short-time energy analysis method.

To avoid the drawback that the closing moment of circuit breakers are difficult to measure in on-line condition monitoring, the application of short-time energy (STE) analysis in the event time detection of the vibration signal was investigated.

Extraction of ship-radiated noise characteristics based on analysis of short-term energy and subjective hearing;

In this paper we introduced the speech signal feature parameters, the speech signal feature parameters selection, and introduced short-term energy、 short-term average range extraction.

This paper analyzes speech endpoint detection based on short-term energy feature in the presence of noise.