TR2008-012

Speech Denoising Using Nonnegative Matrix Factorization with Priors

    •  Wilson, K.W., Raj, B., Smaragdis, P., Divakaran, A., "Speech Denoising Using Nonnegative Matrix Factorization with Priors", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2008, pp. 4029-4032.
      BibTeX TR2008-012 PDF
      • @inproceedings{Wilson2008mar,
      • author = {Wilson, K.W. and Raj, B. and Smaragdis, P. and Divakaran, A.},
      • title = {Speech Denoising Using Nonnegative Matrix Factorization with Priors},
      • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
      • year = 2008,
      • pages = {4029--4032},
      • month = mar,
      • issn = {1520-6149},
      • url = {https://www.merl.com/publications/TR2008-012}
      • }
  • Research Areas:

    Artificial Intelligence, Speech & Audio

TR Image
A simple example showing the advantage of regularizing with the log likelihood. In each panel, the horizontal axis represents time and the vertical axis represents frequency. Darker colors represent higher intensity. The leftmost column shows the original signals.
Abstract:

We present a technique for denoising speech using nonnegative matrix factorization (NMF) in combination with statistical speech and noise models. We compare our new technique to standard NMF and to a state-of-the-art Wiener filter implementation and show improvements in speech quality across a range of interfering noise types.





 

  • Related News & Events

    •  NEWS    ICASSP 2008: 4 publications by MERL researchers and others
      Date: March 31, 2008
      Where: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
      Brief
      • The papers "Joint Tracking and Video Registration by Factorial Hidden Markov Models" by Mei, X. and Porikli, F., "Speech Denoising Using Nonnegative Matrix Factorization with Priors" by Wilson, K.W., Raj, B., Smaragdis, P. and Divakaran, A., "Ultrasonic Doppler Sensor for Speaker Recognition" by Kalgaonkar, K. and Raj, B. and "Sparse and Shift-Invariant Feature Extraction from Non-Negative Data" by Smaragdis, P., Raj, B. and Shashanka, M. were presented at the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP).
    •