icassp 2020 virtual conference

Fddwnet: A Lightweight Convolutional Neural Network For Real-Time Semantic Segmentation

Learning From Dances: Pose-Invariant Re-Identification For Multi-Person Tracking

Hybrid Autoregressive Transducer (Hat)

Resilient To Byzantine Attacks Finite-Sum Optimization Over Networks

Non-Gaussian Ble-Based Indoor Localization Via Gaussian Sum Filtering Coupled With Wasserstein Distance

Time-Frequency Loss For Cnn Based Speech Super-Resolution

Talker-Independent Speaker Separation In Reverberant Conditions

A Deep Neural Network-Driven Feature Learning Method For Polyphonic Acoustic Event Detection From Real-Life Recordings

Fast Lattice-Free Keyword Filtering For Accelerated Spoken Term Detection

A Fast Proximal Point Algorithm For Generalized Graph Laplacian Learning

Learning To Generate Diverse Questions From Keywords

Beamformed Feature For Learning-Based Dual-Channel Speech Separation