icassp 2020 virtual conference

Depthwise-Stft Based Separable Convolutional Neural Networks

Full-Sum Decoding For Hybrid Hmm Based Speech Recognition Using Lstm Language Model

Attentional Fused Temporal Transformation Network For Video Action Recognition

On Network Science And Mutual Information For Explaining Deep Neural Networks

Bband Index: A No-Reference Banding Artifact Predictor

Generating Diverse And Natural Text-To-Speech Samples Using A Quantized Fine-Grained Vae And Autoregressive Prosody Prior

Compressive 2-D Off-Grid Doa Estimation For Propeller Cavitation Localization

Multi-Branch Learning For Weakly-Labeled Sound Event Detection

Unsupervised Image-To-Image Translation Via Fair Representation Of Gender Bias

A New Perspective For Flexible Feature Gathering In Scene Text Recognition Via Character Anchor Pooling

Structured Sparse Attention For End-To-End Automatic Speech Recognition

Hierarchical Caching Via Deep Reinforcement Learning