Phase-aware Single-stage Speech Denoising and Dereverberation with U-Net
By Hyeong-Seok Choi, Hoon Heo, Jie Hwan Lee, Kyogu Lee. 2020
22 citations recorded by the source corpus.
In this work, we tackle a denoising and dereverberation problem with a single-stage framework. Although denoising and dereverberation may be considered two separate challenging tasks, and thus, two modules are typically required for each task, we show that a single deep network can be shared to solve the two problems. To this end, we propose a new masking method called phase-aware beta-sigmoid mask (PHM), which reuses the estimated magnitude values to estimate the clean phase by respecting the triangle inequality in the complex domain between three signal components such as mixture, source and the rest. Two PHMs are used to deal with direct and reverberant source, which allows controlling the proportion of reverberation in the enhanced speech at inference time. In addition, to improve the speech enhancement performance, we propose a new time-domain loss function and show a reasonable performance gain compared to MSE loss in the complex domain. Finally, to achieve a real-time inference, an optimization strategy for U-Net is proposed which significantly reduces the computational overhead up to 88.9% compared to the naive version.
Subfields: Cognitive Neuroscience, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cognitive Neuroscience
- Vishak Gopal
- Ross Cutler
- Chandan K. A. Reddy
- Hannes Gamper
- Sebastian Braun
- Robert Aichner
- Harishchandra Dubey
- Sriram Srinivasan
In Signal Processing
- Ross Cutler
- Vishak Gopal
- Chandan K. A. Reddy
- Robert Aichner
- Hannes Gamper
- Sebastian Braun
- Harishchandra Dubey
- Sriram Srinivasan
Citations in the corpus
- Icassp 2022 Deep Noise Suppression Challenge (2022, background): “In recent years, deep learning based approaches have shown promising results for superior speech quality [2, 3, 4].”
- ICASSP 2021 Deep Noise Suppression Challenge (2020, background): “In recent years, learning-based approaches have shown promising results [3, 4, 5].”
- Interactive Speech and Noise Modeling for Speech Enhancement (2020, unknown): “MultiScale+ (Choi et al. 2020) and PoCoNet (Isik et al.”
- Interspeech 2021 Deep Noise Suppression Challenge (2021, background): “In recent years, learning-based approaches have shown promising results [3, 4, 5].”