Title :
Time-frequency dependent voice activity detection based on a simple threshold test
Author :
Freudenberger, Jürgen ; Stenzel, Sebastian
Author_Institution :
Inst. for Syst. Dynamics, Univ. of Appl. Sci., Konstanz, Germany
Abstract :
This paper proposes an efficient method to determine for each time-frequency point whether speech is present or absent in a noisy microphone signal. Based on a likelihood ratio test for the conditional speech presence probability a simple threshold test is derived. This test compares the current input power for each time-frequency point with an estimate of the noise power spectral density. The theoretical results as well as the simulation results indicate that voice activity is well approximated.
Keywords :
probability; speech processing; time-frequency analysis; conditional speech presence probability; likelihood ratio test; microphone signal; noise power spectral density; threshold test; time-frequency dependent voice activity detection; Error probability; Estimation; Signal to noise ratio; Speech; Speech processing; Time frequency analysis;
Conference_Titel :
Statistical Signal Processing Workshop (SSP), 2011 IEEE
Conference_Location :
Nice
Print_ISBN :
978-1-4577-0569-4
DOI :
10.1109/SSP.2011.5967754