Investigation of Speech Separation as a Front-End for Noise Robust Speech Recognition

  title={Investigation of Speech Separation as a Front-End for Noise Robust Speech Recognition},
  author={Arun Narayanan and DeLiang Wang},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
Recently, supervised classification has been shown to work well for the task of speech separation. We perform an in-depth evaluation of such techniques as a front-end for noise-robust automatic speech recognition (ASR). The proposed separation front-end consists of two stages. The first stage removes additive noise via time-frequency masking. The second stage addresses channel mismatch and the distortions introduced by the first stage; a non-linear function is learned that maps the masked… CONTINUE READING
Highly Cited
This paper has 75 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 55 extracted citations

75 Citations

Citations per Year
Semantic Scholar estimates that this publication has 75 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-8 of 8 references

Feature compensation

  • J. Droppo
  • Techniques for Noise Robustness in Automatic…
  • 2012
Highly Influential
4 Excerpts