TR2014-081

Discriminative NMF and its application to single-channel source separation


    •  Weninger, F., Le Roux, J., Hershey, J.R., Watanabe, S., "Discriminative NMF and its application to single-channel source separation", Interspeech, September 2014, vol. 15, pp. 865-869.
      BibTeX TR2014-081 PDF
      • @inproceedings{Weninger2014sep,
      • author = {Weninger, F. and {Le Roux}, J. and Hershey, J.R. and Watanabe, S.},
      • title = {Discriminative NMF and its application to single-channel source separation},
      • booktitle = {Interspeech},
      • year = 2014,
      • volume = 15,
      • pages = {865--869},
      • month = sep,
      • publisher = {International Speech Communication Association},
      • issn = {2308-457X},
      • url = {https://www.merl.com/publications/TR2014-081}
      • }
  • MERL Contact:
  • Research Areas:

    Artificial Intelligence, Speech & Audio

The objective of single-channel source separation is to accurately recover source signals from mixtures. Non-negative matrix factorization (NMF) is a popular approach for this task, yet previous NMF approaches have not optimized directly this objective, de- spite some efforts in this direction. Our paper introduces discriminative training of the NMF basis functions such that, given the coefficients obtained on a mixture, a desired source is optimally recovered. We approach this optimization by generalizing the model to have separate analysis and reconstruction basis functions. This generalization frees us to optimize reconstruction objectives that incorporate the filtering step and SNR performance criteria. A novel multiplicative update algorithm is presented for the optimization of the reconstruction basis functions according to the proposed discriminative objective functions. Results on the 2nd CHiME Speech Separation and Recognition Challenge task indicate significant gains in source-to-distortion ratio with respect to sparse NMF, exemplar-based NMF, as well as a previously proposed discriminative NMF criterion.

 

  • Related News & Events

    •  NEWS   IEEE Spectrum's "Cars That Think" highlights MERL's speech enhancement research
      Date: March 9, 2015
      MERL Contact: Jonathan Le Roux
      Research Area: Speech & Audio
      Brief
      • Recent research on speech enhancement by MERL's Speech and Audio team was highlighted in "Cars That Think", IEEE Spectrum's blog on smart technologies for cars. IEEE Spectrum is the flagship publication of the Institute of Electrical and Electronics Engineers (IEEE), the world's largest association of technical professionals with more than 400,000 members.
    •  
    •  NEWS   MERL's noise suppression technology featured in Mitsubishi Electric Corporation press release
      Date: February 17, 2015
      MERL Contact: Jonathan Le Roux
      Research Area: Speech & Audio
      Brief
      • Mitsubishi Electric Corporation announced that it has developed breakthrough noise-suppression technology that significantly improves the quality of hands-free voice communication in noisy conditions, such as making a voice call via a car navigation system. Speech clarity is improved by removing 96% of surrounding sounds, including rapidly changing noise from turn signals or wipers, which are difficult to suppress using conventional methods. The technology is based on recent research on speech enhancement by MERL's Speech and Audio team. .
    •