Applications in music and audio processing

An improved optimal transport kernel embedding method with gating mechanism for singing voice separation and speaker identification

A unitary transform based generalized approximate message passing

Introducing topography in convolutional neural networks

HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement

Generative Modeling Based Manifold Learning for Adaptive Filtering Guidance

Applying Symmetrical Component Transform for Industrial Appliance Classification in Non-Intrusive Load Monitoring

SEMI-SUPERVISED LEARNING WITH PER-CLASS ADAPTIVE CONFIDENCE SCORES FOR ACOUSTIC ENVIRONMENT CLASSIFICATION WITH IMBALANCED DATA

Voice Conversion Using Feature Specific Loss Function based Self-Attentive Generative Adversarial Network

ACTIVITY-INFORMED INDUSTRIAL AUDIO ANOMALY DETECTION VIA SOURCE SEPARATION

Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation