ICASSP 2021

On The Marginal Benefit Of Active Learning: Does Self-Supervision Eat Its Cake?

Exploring Automatic Covid-19 Diagnosis Via Voice And Symptoms From Crowdsourced Data

Dnanet: Dense Nested Attention Network For Single Image Dehazing

Speech Bert Embedding For Improving Prosody In Neural Tts

Adaspeech 2: Adaptive Text To Speech With Untranscribed Data

Towards Listening To 10 People Simultaneously: An Efficient Permutation Invariant Training Of Audio Source Separation Using Sinkhorn’S Algorithm

Accelerating Auxiliary Function-Based Independent Vector Analysis

Temporal Link Prediction Via Reinforcement Learning

A Deep Reinforcement Learning Approach To Audio-Based Navigation In A Multi-Speaker Environment

Global-Localized Agent Graph Convolution For Multi-Agent Reinforcement Learning

Pops: Policy Pruning And Shrinking For Deep Reinforcement Learning

Tabular Transformers For Modeling Multivariate Time Series