A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancement
About
Despite noise suppression being a mature area in signal processing, it remains highly dependent on fine tuning of estimator algorithms and parameters. In this paper, we demonstrate a hybrid DSP/deep learning approach to noise suppression. A deep neural network with four hidden layers is used to estimate ideal critical band gains, while a more traditional pitch filter attenuates noise between pitch harmonics. The approach achieves significantly higher quality than a traditional minimum mean squared error spectral estimator, while keeping the complexity low enough for real-time operation at 48 kHz on a low-power processor.
Jean-Marc Valin• 2017
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Speech Enhancement | Multilingual low-SNR (evaluation set) | PESQ2.36 | 23 | |
| Speech Enhancement | Speech Enhancement Evaluation Set | SI-SDR (dB)13 | 6 |
Showing 2 of 2 rows