ICASSP 2023

ANY-TO-ANY VOICE CONVERSION WITH F0 AND TIMBRE DISENTANGLEMENT AND NOVEL TIMBRE CONDITIONING

Enhancing Unsupervised Speech Recognition with Diffusion GANs

LEARNING SPARSE ALIGNMENTS VIA OPTIMAL TRANSPORT FOR CROSS-DOMAIN FAKE NEWS DETECTION

SAMPLING ORDER-LIMITED SIGNALS ON THE SPHERE

Robust Autoencoders for Collective Corruption Removal

REPRESENTATION OF VOCAL TRACT LENGTH TRANSFORMATION BASED ON GROUP THEORY

MAKE YOUR ENEMY YOUR FRIEND: IMPROVING IMAGE ROTATION ANGLE ESTIMATION WITH HARMONICS

SINGLE-CHANNEL SPEECH ENHANCEMENT WITH DEEP COMPLEX U-NETWORKS AND PROBABILISTIC LATENT SPACE MODELS

SPATIAL INFERENCE USING CENSORED MULTIPLE TESTING WITH FDR CONTROL

YOLOX-B: A BETTER YOLOX MODEL FOR REAL-TIME DRIVER BEHAVIOR DETECTION

Towards a More Stable and General Subgraph Information Bottleneck

LE-DTA: Local Extrema convolution for Drug Target Affinity Prediction