ICASSP 2023

DO-FAM: Disentangled Non-Linear Latent Navigation for Facial Attribute Manipulation

Newton-based Trainable Learning Rate

Stochastic super-resolution for Gaussian textures

Semantically-informed Deep Neural Networks for sound recognition

F-PABEE: Flexible-patience-based Early Exiting for Single-label and Multi-label text Classification Tasks

TOPGFORMER: TOPOLOGICAL-BASED GRAPH TRANSFORMER FOR MAPPING BRAIN STRUCTURAL CONNECTIVITY TO FUNCTIONAL CONNECTIVITY

MoLE : MIXTURE OF LANGUAGE EXPERTS FOR MULTI-LINGUAL AUTOMATIC SPEECH RECOGNITION

Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocoder

Analysis of Noisy-target Training for DNN-based speech enhancement

Constrained non-negative PARAFAC2 for electromyogram separation

Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation

STREAMING JOINT SPEECH RECOGNITION AND DISFLUENCY DETECTION