A Dual-Staged Context Aggregation Method Towards Efficient End-To-End Speech Enhancement
arXiv:1908.06468
Abstract
In speech enhancement, an end-to-end deep neural network converts a noisy speech signal to a clean speech directly in time domain without time-frequency transformation or mask estimation. However, aggregating contextual information from a high-resolution time domain signal with an affordable model complexity still remains challenging. In this paper, we propose a densely connected convolutional and recurrent network (DCCRN), a hybrid architecture, to enable dual-staged temporal context aggregation. With the dense connectivity and cross-component identical shortcut, DCCRN consistently outperforms competing convolutional baselines with an average STOI improvement of 0.23 and PESQ of 1.38 at three SNR levels. The proposed method is computationally efficient with only 1.38 million parameters. The generalizability performance on the unseen noise types is still decent considering its low complexity, although it is relatively weaker comparing to Wave-U-Net with 7.25 times more parameters.
Accepted in Proceedings of the ICASSP, Barcelona, Spain, May 4-8, 2020
References in corpus (5)
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- WaveNet: A Generative Model for Raw Audio
- Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation
- Incremental Binarization On Recurrent Neural Networks For Single-Channel Source Separation
- Cascaded Cross-Module Residual Learning towards Lightweight End-to-End Speech Coding