TR2021-137

On The Compensation Between Magnitude and Phase in Speech Separation


    •  Wang, Z.-Q., Wichern, G., Le Roux, J., "On The Compensation Between Magnitude and Phase in Speech Separation", IEEE Signal Processing Letters, November 2021.
      BibTeX TR2021-137 PDF
      • @article{Wang2021nov2,
      • author = {Wang, Zhong-Qiu and Wichern, Gordon and Le Roux, Jonathan},
      • title = {On The Compensation Between Magnitude and Phase in Speech Separation},
      • journal = {IEEE Signal Processing Letters},
      • year = 2021,
      • month = nov,
      • url = {https://www.merl.com/publications/TR2021-137}
      • }
  • MERL Contacts:
  • Research Areas:

    Artificial Intelligence, Machine Learning, Speech & Audio

Abstract:

Many recent studies optimize loss functions defined solely in the time or complex domain, without including a loss on magnitude. Although such loss functions typically produce better scores if the evaluation metrics are objective time-domain metrics, they however produce worse scores on speech quality and intelligibility metrics and usually lead to worse speech recognition performance, compared with including a loss on magnitude. While this phenomenon has been experimentally observed by many studies, it is often not accurately explained and there lacks a thorough understanding on its fundamental cause. This paper provides a novel view from the perspective of the implicit compensation between estimated magnitude and phase.

 

  • Related Publication

  •  Wang, Z.-Q., Wichern, G., Le Roux, J., "On The Compensation Between Magnitude and Phase in Speech Separation", arXiv, August 2021.
    BibTeX arXiv
    • @article{Wang2021aug3,
    • author = {Wang, Zhong-Qiu and Wichern, Gordon and Le Roux, Jonathan},
    • title = {On The Compensation Between Magnitude and Phase in Speech Separation},
    • journal = {arXiv},
    • year = 2021,
    • month = aug,
    • url = {https://arxiv.org/abs/2108.05470}
    • }