Wenqi Tang — accepted AI-conference papers

2023

WUDA: Unsupervised Domain Adaptation Based on Weak Source Domain Labels

Shengjie Liu, Chuang Zhu, Yuan Li, Wenqi Tang

ICASSP 2023accepted

Unsupervised domain adaptation (UDA) for semantic segmentation addresses the cross-domain problem with fine source domain labels. However, the acquisition of semantic labels is often time-consuming, many scenarios only have weak labels (e.g. bounding boxes). When weak supervision and cross-domain pr…

Cited by 0 Source ↗Scholar ↗

2021

Densely Connected Multi-Stage Model with Channel Wise Subband Feature for Real-Time Speech Enhancement

Jingdong Li, Dawei Luo, Yun Liu, Yuanyuan Zhu, Zhaoxia Li, Guohui Cui +2

ICASSP 2021accepted

Research on single channel speech enhancement (SE) has a long tradition, but two main practical problems still remain unsolved. Firstly, it’s hard to balance between enhancement quality and computational efficiency, and low-latency always brings loss of quality. Secondly, enhancement in specific sce…

Cited by 0 Source ↗Scholar ↗