ISCA Archive Interspeech 2014
ISCA Archive Interspeech 2014

Single-channel dynamic exemplar-based speech enhancement

Nasser Mohammadiha, Simon Doclo

This paper proposes an exemplar-based speech enhancement method based on high-resolution STFT magnitude spectrograms, where a selection of the nonnegative training data is used as the dictionary to provide a holistic nonnegative representation of the test data. We discuss how this exemplar-based model ensures that the enhanced speech signal falls on the speech manifold, which improves the quality of the enhanced speech signal. To exploit the temporal continuity, a vector autoregressive model is used to model the activations where the model parameters are learned using a new NMF-based approach. Results from several supervised and semi-supervised speech enhancement experiments indicate that the proposed exemplar-based method outperforms the considered supervised and unsupervised denoising algorithms in terms of both segmental SNR and PESQ at different input SNRs.

doi: 10.21437/Interspeech.2014-575

Cite as: Mohammadiha, N., Doclo, S. (2014) Single-channel dynamic exemplar-based speech enhancement. Proc. Interspeech 2014, 2690-2694, doi: 10.21437/Interspeech.2014-575

  author={Nasser Mohammadiha and Simon Doclo},
  title={{Single-channel dynamic exemplar-based speech enhancement}},
  booktitle={Proc. Interspeech 2014},