virtual conference icassp 2021

Hierarchical Speaker-Aware Sequence-To-Sequence Model For Dialogue Summarization

Subspectral Normalization For Neural Audio Data Processing

Branchy-Gnn: A Device-Edge Co-Inference Framework For Efficient Point Cloud Processing

A Neural Acoustic Echo Canceller Optimized Using An Automatic Speech Recognizer And Large Scale Synthetic Data

Multi-Models Fusion For Light Field Angular Super-Resolution

Robust Latent Representations Via Cross-Modal Translation And Alignment

Auto-Tuning Spectral Clustering For Speaker Diarization Using Normalized Maximum Eigengap

Integrating Subgraph-Aware Relation And Direction Reasoning For Question Answering

Graph Attention And Interaction Network With Multi-Task Learning For Fact Verification

A New Dcase 2017 Rare Sound Event Detection Benchmark Under Equal Training Data: Crnn With Multi-Width Kernels

Slow-Fast Auditory Streams For Audio Recognition

Dynamic Resource Optimization For Adaptive Federated Learning At The Wireless Network Edge