virtual conference icassp 2021

Perceptual Loss Based Speech Denoising With An Ensemble Of Audio Pattern Recognition And Self-Supervised Models

Cgan-Net: Class-Guided Asymmetric Non-Local Network For Real-Time Semantic Segmentation

Eccl: Explicit Correlation-Based Convolution Boundary Locator For Moment Localization

Hidden Markov Model Diarisation With Speaker Location Information

Multi-Scale Speaker Diarization With Neural Affinity Score Fusion

Bidirectional Focused Semantic Alignment Attention Network For Cross-Modal Retrieval

Coarse-To-Careful: Seeking Semantic-Related Knowledge For Open-Domain Commonsense Question Answering

A Two-Stage Approach To Device-Robust Acoustic Scene Classification

Vgai: End-To-End Learning Of Vision-Based Decentralized Controllers For Robot Swarms

Allocating Dnn Layers Computation Between Front-End Devices And The Cloud Server For Video Big Data Processing

Knowledge Reasoning For Semantic Segmentation

High Fidelity Speech Regeneration With Application To Speech Enhancement