Speech Denoising with Deep Feature Losses FG Germain, Q Chen, V Koltun arXiv preprint arXiv:1806.10522, 2018 | 183 | 2018 |
Speaker and noise independent voice activity detection FG Germain, DL Sun, GJ Mysore INTERSPEECH-2013, Lyon, France, 732-736, 2013 | 77 | 2013 |
Cold Diffusion for Speech Enhancement H Yen, FG Germain, G Wichern, J Le Roux ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 74 | 2023 |
Combining Modeling Of Singing Voice And Background Music For Automatic Separation Of Musical Mixtures. Z Rafii, F Germain, DL Sun, GJ Mysore ISMIR 10, 645-680, 2013 | 24 | 2013 |
Neural network for speech denoising trained with deep feature losses FG Germain, Q Chen, V Koltun US Patent 10,726,858, 2020 | 23 | 2020 |
Equalization matching of speech recordings in real-world environments FG Germain, GJ Mysore, T Fujioka 2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016 | 23 | 2016 |
Design principles for lumped model discretisation using Möbius transforms FG Germain, KJ Werner Proc. 18th Int. Conf. Digital Audio Effects, Trondheim, Norway, 371-378, 2015 | 22 | 2015 |
Stopping Criteria for Non-Negative Matrix Factorization Based Supervised and Semi-Supervised Source Separation FG Germain, GJ Mysore IEEE Signal Processing Letters 21 (10), 1284-1288, 2014 | 22 | 2014 |
Synthesis of guitar by digital waveguides: Modeling the plectrum in the physical interaction of the player with the instrument F Germain, G Evangelista 2009 IEEE Workshop on Applications of Signal Processing to Audio and …, 2009 | 19 | 2009 |
A computational model of the Hammond organ vibrato/chorus using wave digital filters KJ Werner, WR Dunkel, FG Germain Proc. Int. Conf. Digital Audio Effects (DAFx-16), Brno, Czech Republic, 271-278, 2016 | 18 | 2016 |
Sinusoidal Parameter Estimation Using Quadratic Interpolation around Power-Scaled Magnitude Spectrum Peaks KJ Werner, FG Germain Applied Sciences 6 (10), 306, 2016 | 16 | 2016 |
A nonlinear analysis framework for electronic synthesizer circuits FG Germain McGill University (Canada), 2011 | 10 | 2011 |
BEATs-based Audio Captioning Model with Instructor Embedding Supervision and ChatGPT Mix-up SL Wu, X Chang, G Wichern, J Jung, F Germain, J Le Roux, S Watanabe Speech Communication (Special issue on Perceptual and Statistical Audition …, 2011 | 9* | 2011 |
Acoustical properties of the vocal-tract in trombone performance V Freour, G Scavone, A Lefebvre, F Germain Proc. 2011 Forum Acusticum, 2011 | 9 | 2011 |
The wavelet transform Applications in Music Information Retrieval F Germain McGill University, Canada, 2009 | 9 | 2009 |
Performance metric based stopping criteria for iterative algorithms FG Germain, GJ Mysore US Patent 9,866,954, 2018 | 8 | 2018 |
Uniform noise sequences for nonlinear system identification FG Germain, JS Abel, P Depalle, MM Wanderley Proc. 15th Intl. Conf. Digital Audio Effects (DAFx-12), York, UK, 241-244, 2012 | 8 | 2012 |
Non-oversampled physical modeling for virtual analog simulations FG Germain Stanford University, 2019 | 7 | 2019 |
Network variable preserving step-size control in wave digital filters MJ Olsen, KJ Werner, FG Germain Proc. 20th Int. Conf. Digit. Audio Effects, 200-207, 2017 | 7 | 2017 |
Improving audio captioning models with fine-grained audio features, text embedding supervision, and llm mix-up augmentation SL Wu, X Chang, G Wichern, J Jung, F Germain, J Le Roux, S Watanabe ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024 | 6 | 2024 |