103 citations
- Centre Inria de l'Université Grenoble AlpesFR2 papers
- Institut national de recherche en sciences et technologies du numériqueFR2 papers
- Chinese University of Hong KongHK1 paper
- Département d'InformatiqueFR1 paper
- École Normale Supérieure - PSLFR1 paper
- Fondazione Bruno KesslerIT1 paper
- National Institute of Technology SikkimIN1 paper
- The University of SydneyAU1 paper
- University of Southern CaliforniaUS1 paper
- University of TrentoIT1 paper
7 papers
Can Layer-wise SSL Features Improve Zero-Shot ASR Performance for Children's Speech?
Abhijit Sinha, Hemant Kumar Kathania, Sudarsana Reddy Kadiri +1
Automatic Speech Recognition (ASR) systems often struggle to accurately process children's speech due to its distinct and highly variable acoustic and linguistic characteristics. W…
Abstract Interpretation-Based Data Leakage Static Analysis
Filip Drobnjaković, Pavle Subotić, Caterina Urban
Data leakage is a well-known problem in machine learning. Data leakage occurs when information from outside the training dataset is used to create a model. This phenomenon renders…
Cyclopean Geometry of Binocular Vision
Miles Hansard, Radu Horaud
The geometry of binocular projection is analyzed, with reference to the primate visual system. In particular, the effects of coordinated eye movements on the retinal images are inv…
Conjugate Mixture Models for Clustering Multimodal Data
Vasil Khalidov, Florence Forbes, Radu Horaud
The problem of multimodal clustering arises whenever the data are gathered with several physically different sensors. Observations from different modalities are not necessarily ali…
Face Frontalization Based on Robustly Fitting a Deformable Shape Model to 3D Landmarks
Zhiqi Kang, Mostafa Sadeghi, Radu Horaud
Face frontalization consists of synthesizing a frontally-viewed face from an arbitrarily-viewed one. The main contribution of this paper is a robust face alignment method that enab…
Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement
Mostafa Sadeghi, Xavier Alameda-Pineda
In this paper, we are interested in unsupervised (unknown noise) audio-visual speech enhancement based on variational autoencoders (VAEs), where the probability distribution of cle…