virtual conference icassp 2021

Scalable Discriminative Discrete Hashing For Large-Scale Cross-Modal Retrieval

Bw-Eda-Eend: Streaming End-To-End Neural Speaker Diarization For A Variable Number Of Speakers

Detection Of Audio-Video Synchronization Errors Via Event Detection

Language Model Is All You Need: Natural Language Understanding As Question Answering

Cross-Modal Spectrum Transformation Network For Acoustic Scene Classification

Recognition Of Dynamic Hand Gesture Based On Mm-Wave Fmcw Radar Micro-Doppler Signatures

Eadnet: Efficient Asymmetric Dilated Network For Semantic Segmentation

Non-Convex Sparse Deviation Modeling Via Generative Models

A Time-Domain Convolutional Recurrent Network For Packet Loss Concealment

Hierarchical Similarity Learning For Language-Based Product Image Retrieval

Compositional Embedding Models For Speaker Identification And Diarization With Simultaneous Speech From 2+ Speakers

A Real-Time Speaker Diarization System Based On Spatial Spectrum