icassp 2020 virtual conference

Apb2Face: Audio-Guided Face Reenactment With Auxiliary Pose And Blink Signals

Compare Learning: Bi-Attention Network For Few-Shot Learning

Fast Clustering With Co-Clustering Via Discrete Non-Negative Matrix Factorization For Image Identification

Parsing Map Guided Multi-Scale Attention Network For Face Hallucination

Mockingjay: Unsupervised Speech Representation Learning With Deep Bidirectional Transformer Encoders

Exploring A Zero-Order Direct Hmm Based On Latent Attention For Automatic Speech Recognition

One-Shot Voice Conversion By Vector Quantization

Learning To Detect Keyword Parts And Whole By Smoothed Max Pooling

A Neural Network For Monaural Intrusive Speech Intelligibility Prediction

Lstm-Based One-Pass Decoder For Low-Latency Streaming

Automotive Collision Risk Estimation Under Cooperative Sensing

Self-Supervised Deep Learning For Fisheye Image Rectification