4 papers
DCHT: Deep Complex Hybrid Transformer for Speech Enhancement
Jialu Li, Junhui Li, Pu Wang +1
Most of the current deep learning-based approaches for speech enhancement only operate in the spectrogram or waveform domain. Although a cross-domain transformer combining waveform…
DPATD: Dual-Phase Audio Transformer for Denoising
Junhui Li, Pu Wang, Jialu Li +2
Recent high-performance transformer-based speech enhancement models demonstrate that time domain methods could achieve similar performance as time-frequency domain methods. However…
PSGformer: Enhancing 3D Point Cloud Instance Segmentation via Precise Semantic Guidance
Lei Pan, Wuyang Luan, Yuan Zheng +2
Most existing 3D instance segmentation methods are derived from 3D semantic segmentation models. However, these indirect approaches suffer from certain limitations. They fail to fu…
Enhancing Navigational Safety in Crowded Environments using Semantic-Deep-Reinforcement-Learning-based Navigation
Linh Kästner, Junhui Li, Zhengcheng Shen +1
Intelligent navigation among social crowds is an essential aspect of mobile robotics for applications such as delivery, health care, or assistance. Deep Reinforcement Learning emer…