Scholar
Mostafa Sadeghi
Google Scholar ID: gSQ5xpcAAAAJ
Inria
generative models
probabilistic machine learning
audio-visual speech processing
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
581
H-index
13
i10-index
16
Publications
20
Co-authors
0
Contact
No contact links provided.
Publications
9 items
The Impact of VAE Design on Latent Pose Representations for Diffusion-based Sign Language Production
2026
Cited
0
Audio-visual Contrastive Alignment for Diffusion-based Visual-conditioned Speech Enhancement
2026
Cited
0
Diffusion-based Frameworks for Unsupervised Speech Enhancement
2026
Cited
1
Data-independent Beamforming for End-to-end Multichannel Multi-speaker ASR
2025
Cited
0
Towards Skeletal and Signer Noise Reduction in Sign Language Production via Quaternion-Based Pose Encoding and Contrastive Learning
2025
Cited
0
Posterior Transition Modeling for Unsupervised Diffusion-Based Speech Enhancement
2025
Cited
0
Joint Beamforming and Speaker-Attributed ASR for Real Distant-Microphone Meeting Transcription
arXiv.org · 2024
Cited
0
Diffusion-based Unsupervised Audio-visual Speech Enhancement
arXiv.org · 2024
Cited
0
Load more
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
