virtual conference icassp 2021

Transformer Based Unsupervised Pre-Training For Acoustic Representation Learning

Mispronunciation Detection In Non-Native (L2) English With Uncertainty Modeling

Respipe: Resilient Model-Distributed Dnn Training At Edge Networks

Multi-Task Learning Via Sharing Inexact Low-Rank Subspace

Non-Local Single Image De-Raining Without Decomposition

A Convex Penalty For Block-Sparse Signals With Unknown Structures

Single Channel Voice Separation For Unknown Number Of Speakers Under Reverberant And Noisy Settings

Learning To Estimate Kernel Scale And Orientation Of Defocus Blur With Asymmetric Coded Aperture

Generalized Knowledge Distillation From An Ensemble Of Specialized Teachers Leveraging Unsupervised Neural Clustering

The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results And Methods

An Investigation Of End-To-End Models For Robust Speech Recognition

Encoder-Decoder Based Pitch Tracking And Joint Model Training For Mandarin Tone Classification