• DOI:10.1109/TASLP.2017.2778151
• Corpus ID: 1116753

On the Importance of Super-Gaussian Speech Priors for Machine-Learning Based Speech Enhancement

@article{Rehr2017OnTI,
  title={On the Importance of Super-Gaussian Speech Priors for Machine-Learning Based Speech Enhancement},
  author={Robert Rehr and Timo Gerkmann},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  year={2017},
  volume={26},
  pages={357-366}
}

• R. Rehr, Timo Gerkmann
• Published 15 March 2017
• Computer Science
• IEEE/ACM Transactions on Audio, Speech, and Language Processing

For enhancing noisy signals, machine-learning based single-channel speech enhancement schemes exploit prior knowledge about typical speech spectral structures. To ensure a good generalization and to meet requirements in terms of computational complexity and memory consumption, certain methods restrict themselves to learning speech spectral envelopes. We refer to these approaches as machine-learning spectral envelope (MLSE)-based approaches. In this paper, we show by means of theoretical and experimental analyses that for MLSE-based approaches, super-Gaussian priors allow for a reduction of noise between speech spectral harmonics which is not achievable using Gaussian estimators such as the Wiener filter. For the evaluation, we use a deep neural network based phoneme classifier and a low-rank nonnegative matrix factorization framework as examples of MLSE-based approaches. A listening experiment and instrumental measures confirm that while super-Gaussian priors yield only moderate improvements for classic enhancement schemes, for MLSE-based approaches super-Gaussian priors clearly make an important difference and significantly outperform Gaussian priors.