| Solving audio inverse problems with a diffusion model E Moliner, J Lehtinen, V Välimäki ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 53 | 2023 |
| A two-stage u-net for high-fidelity denoising of historical recordings E Moliner, V Välimäki ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022 | 32 | 2022 |
| Ultrasound-based silent speech interface using convolutional and recurrent neural networks EM Juanpere, TG Csapó Acta Acustica united with Acustica 105 (4), 587-590, 2019 | 25 | 2019 |
| BEHM-GAN: Bandwidth extension of historical music using generative adversarial networks E Moliner, V Välimäki IEEE/ACM Transactions on Audio, Speech, and Language Processing 31, 943-956, 2022 | 24 | 2022 |
| Diffusion-Based Audio Inpainting E Moliner Juanpere, V Välimäki Audio Engineering Society, 2024 | 16* | 2024 |
| Weakly supervised semantic segmentation for remote sensing hyperspectral imaging E Moliner, LS Romero, V Vilaplana ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 14 | 2020 |
| Diffusion Models for Audio Restoration: A review [Special Issue On Model-Based and Data-Driven Audio Signal Processing] JM Lemercier, J Richter, S Welker, E Moliner, V Välimäki, T Gerkmann IEEE Signal Processing Magazine 41 (6), 72-84, 2025 | 12 | 2025 |
| Blind audio bandwidth extension: A diffusion-based zero-shot approach E Moliner, F Elvander, V Välimäki IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024 | 11* | 2024 |
| Virtual bass system with fuzzy separation of tones and transients E Moliner, J Rämö, V Välimäki International Conference on Digital Audio Effects, 86-93, 2020 | 10 | 2020 |
| BUDDy: Single-channel blind unsupervised dereverberation with diffusion models E Moliner, JM Lemercier, S Welker, T Gerkmann, V Välimäki 2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC …, 2024 | 7 | 2024 |
| A diffusion-based generative equalizer for music restoration E Moliner, M Turunen, F Elvander, V Välimäki arXiv preprint arXiv:2403.18636, 2024 | 6 | 2024 |
| Neural modeling of magnetic tape recorders O Mikkonen, A Wright, E Moliner, V Välimäki arXiv preprint arXiv:2305.16862, 2023 | 6 | 2023 |
| Unsupervised blind joint dereverberation and room acoustics estimation with diffusion models JM Lemercier, E Moliner, S Welker, V Välimäki, T Gerkmann arXiv preprint arXiv:2408.07472, 2024 | 3 | 2024 |
| Realistic gramophone noise synthesis using a diffusion model E Moliner, V Välimäki arXiv preprint arXiv:2206.06259, 2022 | 3 | 2022 |
| Gaussian Flow Bridges for Audio Domain Transfer with Unpaired Data E Moliner, S Braun, H Gamper 2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC …, 2024 | 2 | 2024 |
| Noise morphing for audio time stretching E Moliner, L Fierro, A Wright, MS Hämäläinen, V Välimäki IEEE Signal Processing Letters, 2024 | 1 | 2024 |
| Estimation and Restoration of Unknown Nonlinear Distortion using Diffusion M Švento, E Moliner, L Juvela, A Wright, V Välimäki arXiv preprint arXiv:2501.05959, 2025 | | 2025 |
| HRTF Estimation using a Score-based Prior E Thuillier, JM Lemercier, E Moliner, T Gerkmann, V Välimäki arXiv preprint arXiv:2410.01562, 2024 | | 2024 |
| Realistic Gramophone Noise Synthesis Using a Diffusion Model E Moliner Juanpere, V Välimäki | | 2022 |
| Development and evaluation of virtual bass systems for audio enhancement in small loudspeakers E Moliner Juanpere Universitat Politècnica de Catalunya, 2020 | | 2020 |
Vesa VälimäkiProfessor of Audio Signal Processing, Aalto University, Espoo, Finlandยืนยันอีเมลแล้วที่ aalto.fi