Speech Enhancement Using Separable Polling Attention And Global Layer Normalization Followed With Prelu
2021 · Dengfeng Ke, Jinsong Zhang, Yanlu Xie, et al.
Abstract
Single channel speech enhancement is a challenging task in speech community. Recently, various neural networks based methods have been applied to speech enhancement. Among these models, PHASEN and T-GSA achieve state-of-the-art performances on the publicly opened VoiceBank+DEMAND corpus. Both of the models reach the COVL score of 3.62. PHASEN achieves the highest CSIG score of 4.21 while T-GSA gets the highest PESQ score of 3.06. However, both of these two models are very large. The contradiction between the model performance and the model size is hard to reconcile. In this paper, we introduce three kinds of techniques to shrink the PHASEN model and improve the performance. Firstly, seperable polling attention is proposed to replace the frequency transformation blocks in PHASEN. Secondly, global layer normalization followed with PReLU is used to replace batch normalization followed with ReLU. Finally, BLSTM in PHASEN is replaced with Conv2d operation and the phase stream is simplified.
Authors
(none)
Tags
Stats
Related papers
- Parallel Gated Neural Network With Attention Mechanism For Speech Enhancement (2022)0.00
- PHASEN: A Phase-and-harmonics-aware Speech Enhancement Network (2019)18.20
- Mp-senet: A Speech Enhancement Model With Parallel Denoising Of Magnitude And Phase Spectra (2023)15.51
- Improved Normalizing Flow-based Speech Enhancement Using An All-pole Gammatone Filterbank For Conditional Input Representation (2022)0.00
- Magnitude-and-phase-aware Speech Enhancement With Parallel Sequence Modeling (2023)3.58
- Unifying Speech Enhancement And Separation With Gradient Modulation For End-to-end Noise-robust Speech Separation (2023)0.00
- Phase-aware Speech Enhancement With Deep Complex U-net (2019)0.00
- Magnitude-phase Dual-path Speech Enhancement Network Based On Self-supervised Embedding And Perceptual Contrast Stretch Boosting (2025)3.21