virtual conference icassp 2021

Vset: A Multimodal Transformer For Visual Speech Enhancement

Improving Event Detection By Exploiting Label Hierarchy

Melon Playlist Dataset: A Public Dataset For Audio-Based Playlist Generation And Music Tagging

An Iterative Framework For Self-Supervised Deep Speaker Representation Learning

Elbert: Fast Albert With Confidence-Window Based Early Exit

Learning From Heterogeneous Eeg Signals With Differentiable Channel Reordering

Parallel Iterated Extended And Sigma-Point Kalman Smoothers

Multiview Variational Graph Autoencoders For Canonical Correlation Analysis

Switching Variational Auto-Encoders For Noise-Agnostic Audio-Visual Speech Enhancement

Contrastive Self-Supervised Learning For Text-Independent Speaker Verification

Leveraging The Structure Of Musical Preference In Content-Aware Music Recommendation

A Stage Match For Query-By-Example Spoken Term Detection Based On Structure Information Of Query