DBNet: A Dual-branch Network Architecture Processing on Spectrum and Waveform for Single-channel Speech Enhancement

Abstract

In real acoustic environment, speech enhancement is an arduous task to improve the quality and intelligibility of speech interfered by background noise and reverberation. Over the past years, deep learning has shown great potential on speech enhancement. In this paper, we propose a novel real-time framework called DBNet which is a dual-branch structure with alternate interconnection. Each branch incorporates an encoderdecoder architecture with skip connections. The two branches are responsible for spectrum and waveform modeling, respectively. A bridge layer is adopted to exchange information between the two branches. Systematic evaluation and comparison show that the proposed system substantially outperforms related algorithms under very challenging environments. And in INTERSPEECH 2021 Deep Noise Suppression (DNS) challenge, the proposed system ranks the top 8 in real-time track 1 in terms of the Mean Opinion Score (MOS) of the ITU-T P.835 framework.

ATS-YOLOv7: A Real-Time Multi-Scale Object Detection Method for UAV Aerial Images Based on Improved YOLOv7

“…In this section, we compare the performance of the proposed method with a variety of SOTA visual detection models, including one-and two-stage models, on the DIOR data set, in order to illustrate the advantages of the ATS-YOLOv7 algorithm in terms of the current aerial image detection task. The chosen experimental models included RetinaNet [64], Scaled-YOLOv4 [65], YOLOv5 [22], TPH-YOLOv5 [66], HR-Cascade++ [67], O 2 DETR [68], DBAI-Net [69], YOLOv7 [23], and GLENet [70]. The specific test results for each Overall, among the detected object categories, ATS-YOLOv7 had a higher classification accuracy for most objects when compared to YOLOv7, and the maximum difference in accuracy between the two was 12%.…”

A Novel Temporal Attentive-Pooling based Convolutional Recurrent Architecture for Acoustic Signal Enhancement

“…The second direction is to use a better model architecture. Examples of successful approaches include models with complex parameters [61][62][63], ensemble learning [64][65][66], dual path [67][68][69], and dual branch [70] architectures. The third direction is to incorporate complementary information from other modalities into ASE applications.…”