ISCA Archive Interspeech 2006
ISCA Archive Interspeech 2006

Modified phase opponency based solution to the speech separation challenge

Om D. Deshmukh, Carol Y. Espy-Wilson

In this work, we present a single-channel speech enhancement technique called the Modified Phase Opponency (MPO) model as a solution to the Speech Separation Challenge. The MPO model is based on a neural model for detection of tones-in-noise called the Phase Opponency (PO) model. Replacing the noisy speech signals by the corresponding MPO-processed signals increases the accuracy by 31% when the speech signals are corrupted by speech-shaped noise at 0 dB Signal-to-Noise Ratio (SNR). It is worth mentioning that the MPO enhancement scheme was developed using the noisy connected-digit Aurora database and was not tailored in any way to fit the Grid database used in this challenge. One of the salient features of the MPO-based speech enhancement scheme is that it does not need to estimate the noise characteristics, nor does it assume that the noise satisfies any statistical model.


doi: 10.21437/Interspeech.2006-26

Cite as: Deshmukh, O.D., Espy-Wilson, C.Y. (2006) Modified phase opponency based solution to the speech separation challenge. Proc. Interspeech 2006, paper 1936-Mon1WeS.8, doi: 10.21437/Interspeech.2006-26

@inproceedings{deshmukh06_interspeech,
  author={Om D. Deshmukh and Carol Y. Espy-Wilson},
  title={{Modified phase opponency based solution to the speech separation challenge}},
  year=2006,
  booktitle={Proc. Interspeech 2006},
  pages={paper 1936-Mon1WeS.8},
  doi={10.21437/Interspeech.2006-26}
}