/Voice_Activity_Detector

A statistical model-based Voice Activity Detection

Primary LanguageJupyter Notebook

A statistical model-based Voice Activity Detector

A voice activity detector applied a statistical model has been made in [2], where the decision rule is derived from the likelihood ratio test (LRT) by estimating unknown parameters using the decision-directed method. Hang-over scheme based on the hidden Markov model (HMM) are applied for smoothing.

Run the demo

python vad.py

Results

References

TODO(will be uploaded):

  • Q. H. Jo, J. H. Chang, J. W. Shin, and N. S. Kim, “Statistical model-based voice activity detection using support vector machine,” IET Signal Process., vol. 3, no. 3, pp. 205–210, 2009.
  • X.-L. Zhang and J. Wu, “Deep belief networks based voice activity detection,” IEEE Trans. Audio Speech Lang. Process., vol. 21, no. 4, pp. 697–710, Apr. 2013.