ICASSP 2023

Efficient Practices for Profile-to-Frontal Face Synthesis and Recognition

DISTANCE-BASED ONLINE LABEL INFERENCE ATTACKS AGAINST SPLIT LEARNING

Dereverberation in Acoustic Sensor Networks using Weighted Prediction Error with Microphone-dependent Prediction Delays

Towards Adversarially Robust Continual Learning

LEARNING CAUSAL REPRESENTATIONS FOR GENERALIZABLE FACE ANTI SPOOFING

A principled approach to model validation in domain generalization

X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusion

SPEAKERAUGMENT: DATA AUGMENTATION FOR GENERALIZABLE SOURCE SEPARATION VIA SPEAKER PARAMETER MANIPULATION

SW-WaveNet: Learning Representation from Spectrogram and Wavegram Using WaveNet for Anomalous Sound Detection

Scale-adaptive tiny object detection enhanced by across-scale and shape-preserved semantic location

ENLIGHTENING THE STUDENT IN KNOWLEDGE DISTILLATION

D-Conformer: Deformable Sparse Transformer Augmented Convolution for Voxel-based 3D Object Detection