ICASSP 2023

SEPDIFF: SPEECH SEPARATION BASED ON DENOISING DIFFUSION MODEL

FEW BUT INFORMATIVE LOCAL HASH CODE MATCHING FOR IMAGE RETRIEVAL

Vision, Deduction and Alignment: An Empirical Study on Multi-modal Knowledge Graph Alignment

Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming

MAST: Multiscale Audio Spectrogram Transformers

Dynamic Scalable Self-Attention Ensemble for Task-Free Continual Learning

StuArt: Individualized Classroom Observation of Students with Automatic Behavior Recognition and Tracking

Reducing the communication and computational cost of random Fourier features Kernel LMS in diffusion networks

SLICER: Learning universal audio representations using low-resource self-supervised pre-training

DEEP PROXIMAL GRADIENT METHOD FOR LEARNED CONVEX REGULARIZERS

Analysis and transformation of voice level in singing voice

Data-Driven Graph Convolutional Neural Networks for Power System Contingency Analysis