ICASSP 2023

PHONETIC ANCHOR-BASED TRANSFER LEARNING TO FACILITATE UNSUPERVISED CROSS-LINGUAL SPEECH EMOTION RECOGNITION

Improving Retrieval-based Dialogue System via Syntax-Informed Attention

Weakly-Supervised Scene-Specific Crowd Counting Using Real-Synthetic Hybrid Data

Improving the Stochastic Gradient Descent's test accuracy by manipulating the l_\infty norm of its gradient approximation

Semi-Supervised Domain Generalization with Graph-based Classifier

Zero-Shot Speech Emotion Recognition Using Generative Learning with Reconstructed Prototypes

DISAMBIGUATION OF COGNITIVE IMPAIRMENT DIAGNOSIS WITH EEG-BASED DUAL-CONTRASTIVE LEARNING

CN-CVS: A Mandarin Audio-Visual Dataset for Large Vocabulary Continuous Visual to Speech Synthesis

Hierarchical Graph Learning for Stock Market Prediction via a Domain-Aware Graph Pooling Operator

FlowGrad: Using Motion for Visual Sound Source Localization

Simplicial Vector Autoregressive Model for Streaming Edge Flows

A Radar-Jammer Zero-Sum Repeated Bayesian Game