virtual conference icassp 2021

No Relaxation: Guaranteed Recovery Of Finite-Valued Signals From Undersampled Measurements

Streaming Multi-Speaker Asr With Rnn-T

Construction Of A Large-Scale Japanese Asr Corpus On Tv Recordings

Improved Robustness To Disfluencies In Rnn-Transducer Based Speech Recognition

Have You Made A Decision? Where? A Pilot Study On Interpretability Of Polarity Analysis Based On Advising Problem

Multiview Sensing With Unknown Permutations: An Optimal Transport Approach

Sparse High-Order Portfolios Via Proximal Dca And Sca

Decentralized Deep Learning Using Momentum-Accelerated Consensus

Blind Extraction Of Moving Sources Via Independent Component And Vector Analysis: Examples

A Closer Look At Audio-Visual Multi-Person Speech Recognition And Active Speaker Selection

Nisp: A Multi-Lingual Multi-Accent Dataset For Speaker Profiling

Classifying Speech Intelligibility Levels Of Children In Two Continuous Speech Styles