Speech enhancement using arch model

@article{Atkins2016SpeechEU,
  title={Speech enhancement using arch model},
  author={Aviva Atkins and Israel Cohen},
  journal={2016 IEEE International Workshop on Acoustic Signal Enhancement (IWAENC)},
  year={2016},
  pages={1-5}
}
In this paper, we investigate the use of the autoregressive conditional heteroscedasticity (ARCH) model as a replacement to the decision-directed method in the log-spectral amplitude estimator for speech enhancement. We employ three sound quality measures: speech distortion, noise reduction and musical noise, and explain the effect the ARCH model parameters have on these measures. We demonstrate and compare the use of the decision-directed and ARCH estimators and show that the ARCH model… CONTINUE READING

Similar Papers

Figures and Topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 11 REFERENCES

Black box measurement of musical tones produced by noise reduction systems

  • 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2012

Relaxed statistical model for speech enhancement and a priori SNR estimation

  • IEEE Transactions on Speech and Audio Processing
  • 2005
VIEW 3 EXCERPTS