ICASSP 2021

Disentangled Speaker And Language Representations Using Mutual Information Minimization And Domain Adaptation For Cross-Lingual Tts

Replacing Human Audio With Synthetic Audio For On-Device Unspoken Punctuation Prediction

Joint Amplitude And Phase Refinement For Monaural Source Separation

A Noise-Robust Signal Processing Strategy For Cochlear Implants Using Neural Networks

A Fast And Efficient Network For Single Image Deraining

Robust Device-Free Proximity Detection Using Wifi

Low-Resource Expressive Text-To-Speech Using Data Augmentation

Improving Cross-Domain Slot Filling With Common Syntactic Structure

Temporal Rain Decomposition With Spatial Structure Guidance For Video Deraining

Nasa: A Noise-Adaptive And Structure-Aware Learning Framework For Image Deblurring

Cooperative Scenarios For Multi-Agent Reinforcement Learning In Wireless Edge Caching

Adversarial Generative Distance-Based Classifier For Robust Out-Of-Domain Detection