icassp 2020 virtual conference

Beam-Tasnet: Time-Domain Audio Separation Network Meets Frequency-Domain Beamformer

Multi-Task Self-Supervised Learning For Robust Speech Recognition

Learning Asr-Robust Contextualized Embeddings For Spoken Language Understanding

Simultaneous Separation And Transcription Of Mixtures With Multiple Polyphonic And Percussive Instruments

Approaching Optimal Embedding In Audio Steganography With Gan

On Distributed Stochastic Gradient Algorithms For Global Optimization

Dynamic Metasurface Antennas For Bit-Constrained Mimo-Ofdm Receivers

Effectiveness Of Self-Supervised Pre-Training For Asr

End-To-End Articulatory Modeling For Dysarthric Articulatory Attribute Detection

A Siamese Content-Attentive Graph Convolutional Network For Personality Recognition Using Physiology

Optimal Window Design For Joint Spatial-Spectral Domain Filtering Of Signals On The Sphere

Lai-Net: Local-Ancestry Inference With Neural Networks