ICASSP 2023

Compressive Sensing with Tensorized Autoencoder

SRTNet: Time Domain Speech Enhancement Via Stochastic Refinement

SYMBOL LEVEL PRECODING IN THE RF DOMAIN FOR LOW HARDWARE COMPLEXITY RIS-ASSISTED MU-MISO SYSTEMS

Hint-dynamic Knowledge Distillation

{NASE: A Chinese Benchmark for Evaluating Robustness of Spoken Language Understanding Models in Slot Filling

MaskDUL: Data Uncertainty Learning in Masked Face Recognition

TOPOLOGICAL SIGNAL PROCESSING OVER WEIGHTED SIMPLICIAL COMPLEXES

Selecting Language Models Features via Software-Hardware Co-Design

A Perceptual Neural Audio Coder with A Mean-Scale Hyperprior

Single Domain Dynamic Generalization for Iris Presentation Attack Detection

Robust Log-based Anomaly Detection with Hierarchical Contrastive Learning

token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text