ICASSP 2023

Neural Fourier Shift for Binaural Speech Rendering

CAN2V: CAN-BUS DATA-BASED SEQ2SEQ MODEL FOR VEHICLE VELOCITY PREDICTION

Relative dynamic time warping comparison for pronunciation errors

Unsupervised Out-of-Distribution Detection Using Few In-Distribution Samples

G2CNN: GEOMETRIC PRIOR BASED GCNN FOR SINGLE-VIEW 3D RECONSTRUCTION WITH LOOP SUBDIVISION

Towards Building Text-To-Speech Systems for the Next Billion Users

Data leakage in cross-modal retrieval training: A case study

SELF SUPERVISED BERT FOR LEGAL TEXT CLASSIFICATION

Egocentric Action Anticipation for Personal Health

Global Localisation in Continuous Magnetic Vector Fields Using Gaussian Processes

I3D: Transformer architectures with input-dependent dynamic depth for speech recognition

ByteCover3: Accurate Cover Song Identification on Short Queries