| Generation or replication: Auscultating audio latent diffusion models D Bralios, G Wichern, FG Germain, Z Pan, S Khurana, C Hori, J Le Roux ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024 | 17 | 2024 |
| Latent iterative refinement for modular source separation D Bralios, E Tzinis, G Wichern, P Smaragdis, J Le Roux ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 13 | 2023 |
| MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks H Ha, Q Zhan, J Kim, D Bralios, S Sanniboina, N Peng, KW Chang, ... arXiv preprint arXiv:2502.17832, 2025 | 11 | 2025 |
| Learning to Upsample and Upmix Audio in the Latent Domain D Bralios, P Smaragdis, J Casebeer arXiv preprint arXiv:2506.00681, 2025 | 2 | 2025 |
| Unified gradient reweighting for model biasing with applications to source separation E Tzinis, D Bralios, P Smaragdis ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021 | 2 | 2021 |
| Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders D Bralios, J Casebeer, P Smaragdis 2025 IEEE 35th International Workshop on Machine Learning for Signal …, 2025 | 1 | 2025 |
| Comparing audio signals with external normalization G Wichern, D Bralios, FG Germain, J Le Roux US Patent App. 18/502,918, 2025 | | 2025 |
| Complete and separate: Conditional separation with missing target source attribute completion D Bralios, E Tzinis, P Smaragdis 2023 IEEE Workshop on Applications of Signal Processing to Audio and …, 2023 | | 2023 |
Paris SmaragdisProfessor, Massachusetts Institute of TechnologyVerified email at mit.edu
