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
Showing eess.ASShow all
2 papers · 1 filter
eess.AS2025★ 4 cited
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…
eess.AS2019★ 25 cited
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…