François G. Germain

65 papers A* 1A 9C 2Misc 12Journal 28Unranked 13
YearRankTypeTitle / Venue / Authors
2026 J jnl
Velocity Potential Neural Field for Efficient Ambisonics Impulse Response Modeling.
CoRR
Yoshiki Masuyama, François G. Germain, Gordon Wichern, Chiori Hori, Jonathan Le Roux
2025 J jnl
Data Augmentation Using Neural Acoustic Fields With Retrieval-Augmented Pre-training.
CoRR
Christopher Ick, Gordon Wichern, Yoshiki Masuyama, François G. Germain, Jonathan Le Roux
2025 A conf
Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses.
INTERSPEECH
Christopher Ick, Gordon Wichern, Yoshiki Masuyama, François G. Germain, Jonathan Le Roux
2025 J jnl
Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses.
CoRR
Christopher Ick, Gordon Wichern, Yoshiki Masuyama, François G. Germain, Jonathan Le Roux
2025 A conf
Factorized RVQ-GAN For Disentangled Speech Tokenization.
INTERSPEECH
Sameer Khurana, Dominik Klement, Antoine Laurent, Dominik Bobos, Juraj Novosad, Peter Gazdik, Ellen Zhang, Zili Huang, Amir Hussein, Ricard Marxer, Yoshiki Masuyama, Ryo Aihara, Chiori Hori, François G. Germain, Gordon Wichern, Jonathan Le Roux
2025 J jnl
Factorized RVQ-GAN For Disentangled Speech Tokenization.
CoRR
Sameer Khurana, Dominik Klement, Antoine Laurent, Dominik Bobos, Juraj Novosad, Peter Gazdik, Ellen Zhang, Zili Huang, Amir Hussein, Ricard Marxer, Yoshiki Masuyama, Ryo Aihara, Chiori Hori, François G. Germain, Gordon Wichern, Jonathan Le Roux
2025 — conf
FasTUSS: Faster Task-Aware Unified Source Separation.
WASPAA
Francesco Paissan, Gordon Wichern, Yoshiki Masuyama, Ryo Aihara, François G. Germain, Kohei Saijo, Jonathan Le Roux
2025 J jnl
FasTUSS: Faster Task-Aware Unified Source Separation.
CoRR
Francesco Paissan, Gordon Wichern, Yoshiki Masuyama, Ryo Aihara, François G. Germain, Kohei Saijo, Jonathan Le Roux
2025 J jnl
FlexIO: Flexible Single- and Multi-Channel Speech Separation and Enhancement.
CoRR
Yoshiki Masuyama, Kohei Saijo, Francesco Paissan, Jiangyu Han, Marc Delcroix, Ryo Aihara, François G. Germain, Gordon Wichern, Jonathan Le Roux
2025 A conf
HASRD: Hierarchical Acoustic and Semantic Representation Disentanglement.
INTERSPEECH
Amir Hussein, Sameer Khurana, Gordon Wichern, François G. Germain, Jonathan Le Roux
2025 J jnl
HASRD: Hierarchical Acoustic and Semantic Representation Disentanglement.
CoRR
Amir Hussein, Sameer Khurana, Gordon Wichern, François G. Germain, Jonathan Le Roux
2025 A conf
Investigating continuous autoregressive generative speech enhancement.
INTERSPEECH
Haici Yang, Gordon Wichern, Ryo Aihara, Yoshiki Masuyama, Sameer Khurana, François G. Germain, Jonathan Le Roux
2025 Misc conf
Keeping the Balance: Anomaly Score Calculation for Domain Generalization.
ICASSP
Kevin Wilkinghoff, Haici Yang, Janek Ebbers, François G. Germain, Gordon Wichern, Jonathan Le Roux
2025 Misc conf
Leveraging Audio-Only Data for Text-Queried Target Sound Extraction.
ICASSP
Kohei Saijo, Janek Ebbers, François G. Germain, Sameer Khurana, Gordon Wichern, Jonathan Le Roux
2025 J jnl
Local Density-Based Anomaly Score Normalization for Domain Generalization.
CoRR
Kevin Wilkinghoff, Haici Yang, Janek Ebbers, François G. Germain, Gordon Wichern, Jonathan Le Roux
2025 Misc conf
No Class Left Behind: A Closer Look at Class Balancing for Audio Tagging.
ICASSP
Janek Ebbers, François G. Germain, Kevin Wilkinghoff, Gordon Wichern, Jonathan Le Roux
2025 — conf
Physics-Informed Direction-Aware Neural Acoustic Fields.
WASPAA
Yoshiki Masuyama, François G. Germain, Gordon Wichern, Christopher Ick, Jonathan Le Roux
2025 J jnl
Physics-Informed Direction-Aware Neural Acoustic Fields.
CoRR
Yoshiki Masuyama, François G. Germain, Gordon Wichern, Christopher Ick, Jonathan Le Roux
2025 J jnl
Probabilistic Forecasting for Building Energy Systems using Time-Series Foundation Models.
CoRR
Young Jin Park, François G. Germain, Jing Liu, Ye Wang, Toshiaki Koike-Akino, Gordon Wichern, Navid Azizan, Christopher R. Laughman, Ankush Chakrabarty
2025 Misc conf
Retrieval-Augmented Neural Field for HRTF Upsampling and Personalization.
ICASSP
Yoshiki Masuyama, Gordon Wichern, François G. Germain, Christopher Ick, Jonathan Le Roux
2025 J jnl
Retrieval-Augmented Neural Field for HRTF Upsampling and Personalization.
CoRR
Yoshiki Masuyama, Gordon Wichern, François G. Germain, Christopher Ick, Jonathan Le Roux
2025 Misc conf
Task-Aware Unified Source Separation.
ICASSP
Kohei Saijo, Janek Ebbers, François G. Germain, Gordon Wichern, Jonathan Le Roux
2025 A* conf
UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing.
CVPR
Yung-Hsuan Lai, Janek Ebbers, Yu-Chiang Frank Wang, François G. Germain, Michael J. Jones, Moitreya Chatterjee
2025 J jnl
UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing.
CoRR
Yung-Hsuan Lai, Janek Ebbers, Yu-Chiang Frank Wang, François G. Germain, Michael J. Jones, Moitreya Chatterjee
2024 A conf
Enhanced Reverberation as Supervision for Unsupervised Speech Separation.
INTERSPEECH
Kohei Saijo, Gordon Wichern, François G. Germain, Zexu Pan, Jonathan Le Roux
2024 J jnl
Enhanced Reverberation as Supervision for Unsupervised Speech Separation.
CoRR
Kohei Saijo, Gordon Wichern, François G. Germain, Zexu Pan, Jonathan Le Roux
2024 Misc conf
Generation or Replication: Auscultating Audio Latent Diffusion Models.
ICASSP
Dimitrios Bralios, Gordon Wichern, François G. Germain, Zexu Pan, Sameer Khurana, Chiori Hori, Jonathan Le Roux
2024 Misc conf
Improving Audio Captioning Models with Fine-Grained Audio Features, Text Embedding Supervision, and LLM Mix-Up Augmentation.
ICASSP
Shih-Lun Wu, Xuankai Chang, Gordon Wichern, Jee-weon Jung, François G. Germain, Jonathan Le Roux, Shinji Watanabe
2024 — conf
Late Audio-Visual Fusion for in-the-Wild Speaker Diarization.
ICASSP Workshops
Zexu Pan, Gordon Wichern, François G. Germain, Aswin Shanmugam Subramanian, Jonathan Le Roux
2024 J jnl
Leveraging Audio-Only Data for Text-Queried Target Sound Extraction.
CoRR
Kohei Saijo, Janek Ebbers, François G. Germain, Sameer Khurana, Gordon Wichern, Jonathan Le Roux
2024 Misc conf
NIIRF: Neural IIR Filter Field for HRTF Upsampling and Personalization.
ICASSP
Yoshiki Masuyama, Gordon Wichern, François G. Germain, Zexu Pan, Sameer Khurana, Chiori Hori, Jonathan Le Roux
2024 J jnl
NIIRF: Neural IIR Filter Field for HRTF Upsampling and Personalization.
CoRR
Yoshiki Masuyama, Gordon Wichern, François G. Germain, Zexu Pan, Sameer Khurana, Chiori Hori, Jonathan Le Roux
2024 Misc conf
NeuroHeed+: Improving Neuro-Steered Speaker Extraction with Joint Auditory Attention Detection.
ICASSP
Zexu Pan, Gordon Wichern, François G. Germain, Sameer Khurana, Jonathan Le Roux
2024 A conf
PARIS: Pseudo-AutoRegressIve Siamese Training for Online Speech Separation.
INTERSPEECH
Zexu Pan, Gordon Wichern, François G. Germain, Kohei Saijo, Jonathan Le Roux
2024 J jnl
SMITIN: Self-Monitored Inference-Time INtervention for Generative Music Transformers.
CoRR
Junghyun Koo, Gordon Wichern, François G. Germain, Sameer Khurana, Jonathan Le Roux
2024 A conf
Sound Event Bounding Boxes.
INTERSPEECH
Janek Ebbers, François G. Germain, Gordon Wichern, Jonathan Le Roux
2024 J jnl
Sound Event Bounding Boxes.
CoRR
Janek Ebbers, François G. Germain, Gordon Wichern, Jonathan Le Roux
2024 — conf
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement.
IWAENC
Kohei Saijo, Gordon Wichern, François G. Germain, Zexu Pan, Jonathan Le Roux
2024 J jnl
TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement.
CoRR
Kohei Saijo, Gordon Wichern, François G. Germain, Zexu Pan, Jonathan Le Roux
2024 J jnl
Task-Aware Unified Source Separation.
CoRR
Kohei Saijo, Janek Ebbers, François G. Germain, Gordon Wichern, Jonathan Le Roux
2024 — conf
Why Does Music Source Separation Benefit from Cacophony?
ICASSP Workshops
Chang-Bin Jeon, Gordon Wichern, François G. Germain, Jonathan Le Roux
2023 Misc conf
Cold Diffusion for Speech Enhancement.
ICASSP
Hao Yen, François G. Germain, Gordon Wichern, Jonathan Le Roux
2023 J jnl
Generation or Replication: Auscultating Audio Latent Diffusion Models.
CoRR
Dimitrios Bralios, Gordon Wichern, François G. Germain, Zexu Pan, Sameer Khurana, Chiori Hori, Jonathan Le Roux
2023 — conf
Hyperbolic Unsupervised Anomalous Sound Detection.
WASPAA
François G. Germain, Gordon Wichern, Jonathan Le Roux
2023 J jnl
Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation.
CoRR
Shih-Lun Wu, Xuankai Chang, Gordon Wichern, Jee-weon Jung, François G. Germain, Jonathan Le Roux, Shinji Watanabe
2023 — conf
Location as Supervision for Weakly Supervised Multi-Channel Source Separation of Machine Sounds.
WASPAA
Ricardo Falcón Pérez, Gordon Wichern, François G. Germain, Jonathan Le Roux
2023 J jnl
NeuroHeed+: Improving Neuro-steered Speaker Extraction with Joint Auditory Attention Detection.
CoRR
Zexu Pan, Gordon Wichern, François G. Germain, Sameer Khurana, Jonathan Le Roux
2023 J jnl
Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT.
CoRR
Ke Chen, Gordon Wichern, François G. Germain, Jonathan Le Roux
2023 — conf
Paᗧ-HuBERT: Self-Supervised Music Source Separation Via Primitive Auditory Clustering And Hidden-Unit Bert.
ICASSP Workshops
Ke Chen, Gordon Wichern, François G. Germain, Jonathan Le Roux
2023 J jnl
Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction.
CoRR
Zexu Pan, Gordon Wichern, Yoshiki Masuyama, François G. Germain, Sameer Khurana, Chiori Hori, Jonathan Le Roux
2023 C conf
Scenario-Aware Audio-Visual TF-Gridnet for Target Speech Extraction.
ASRU
Zexu Pan, Gordon Wichern, Yoshiki Masuyama, François G. Germain, Sameer Khurana, Chiori Hori, Jonathan Le Roux
2022 J jnl
Cold Diffusion for Speech Enhancement.
CoRR
Hao Yen, François G. Germain, Gordon Wichern, Jonathan Le Roux
2022 J jnl
Towards End-to-end Speaker Diarization in the Wild.
CoRR
Zexu Pan, Gordon Wichern, François G. Germain, Aswin Shanmugam Subramanian, Jonathan Le Roux
2021 — conf
Periodic Analysis of Nonlinear Virtual Analog Models.
WASPAA
François G. Germain
2021 C conf
Practical Virtual Analog Modeling Using MÖbius Transforms.
DAFx
François G. Germain
2019 A conf
Speech Denoising with Deep Feature Losses.
INTERSPEECH
François G. Germain, Qifeng Chen, Vladlen Koltun
2018 J jnl
Speech Denoising with Deep Feature Losses.
CoRR
François G. Germain, Qifeng Chen, Vladlen Koltun
2017 — conf
Optimizing differentiated discretization for audio circuits beyond driving point transfer functions.
WASPAA
François G. Germain, Kurt James Werner
2016 Misc conf
Equalization matching of speech recordings in real-world environments.
ICASSP
François G. Germain, Gautham J. Mysore, Takako Fujioka
2015 — conf
Efficient illuminant correction in the local, linear, learned (L3) method.
Digital Photography
François G. Germain, Iretiayo A. Akinola, Qiyuan Tian, Steven Lansel, Brian A. Wandell
2015 Misc conf
Speaker and noise independent online single-channel speech enhancement.
ICASSP
François G. Germain, Gautham J. Mysore
2014 J jnl
Stopping Criteria for Non-Negative Matrix Factorization Based Supervised and Semi-Supervised Source Separation.
IEEE Signal Process. Lett.
François G. Germain, Gautham J. Mysore
2013 — conf
Combining Modeling Of Singing Voice And Background Music For Automatic Separation Of Musical Mixtures.
ISMIR
Zafar Rafii, François G. Germain, Dennis L. Sun, Gautham J. Mysore
2013 A conf
Speaker and noise independent voice activity detection.
INTERSPEECH
François G. Germain, Dennis L. Sun, Gautham J. Mysore
2009 — conf
Synthesis of guitar by digital waveguides: Modeling the plectrum in the physical interaction of the player with the instrument.
WASPAA
François G. Germain, Gianpaolo Evangelista