Gaussian-Bernoulli restricted Boltzmann machines and automatic feature extraction for noise robust missing data mask estimation

Sami Keronen, KyungHyun Cho, Tapani Raiko, Alexander Ilin, Kalle J. PalomäkiICASSP 2013 · OpenReview

Abstract

A missing data mask estimation method based on Gaussian-Bernoulli restricted Boltzmann machine (GRBM) trained on cross-correlation representation of the audio signal is presented in the study. The automatically learned features by the GRBM are utilized in dividing the time-frequency units of the spectrographic mask into noise and speech dominant. The system is evaluated against two baseline mask estimation methods in a reverberant multisource environment speech recognition task. The proposed system is shown to provide a performance improvement in the speech recognition accuracy over the previous multifeature approaches.
BibTeX
@inproceedings{keronen2013gaussian,
  author = {Sami Keronen and KyungHyun Cho and Tapani Raiko and Alexander Ilin and Kalle J. Palomäki},
  title = {{Gaussian-Bernoulli restricted Boltzmann machines and automatic feature extraction for noise robust missing data mask estimation}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2013},
  url = {https://openreview.net/forum?id=H_dql0EBaJ9},
}

Loading related content...

Figure