Stefan Uhlich

ORCID

Publication Activity (10 Years)

Years Active: 2008-2024
Publications (10 Years): 41

Top Venues

CoRR

ICASSP

Trans. Int. Soc. Music. Inf. Retr.

ISMIR

University of Stuttgart (PHD)

Education History

University of Stuttgart

PHD

Publications

Bac Nguyen, Stefan Uhlich, Fabien Cardinaux, Lukas Mauch, Marzieh Edraki, Aaron C. Courville
SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning. CoRR (2024)
Stefan Uhlich, Giorgio Fabbro, Masato Hirano, Shusuke Takahashi, Gordon Wichern, Jonathan Le Roux, Dipam Chakraborty, Sharada Mohanty, Kai Li, Yi Luo, Jianwei Yu, Rongzhi Gu, Roman A. Solovyev, Alexander L. Stempkovskiy, Tatiana Habruseva, Mikhail Sukhovei, Yuki Mitsufuji
The Sound Demixing Challenge 2023 - Cinematic Demixing Track. Trans. Int. Soc. Music. Inf. Retr. 7 (1) (2024)
Ryosuke Sawata, Naoya Takahashi, Stefan Uhlich, Shusuke Takahashi, Yuki Mitsufuji
The whole is greater than the sum of its parts: improving music source separation by bridging networks. EURASIP J. Audio Speech Music. Process. 2024 (1) (2024)
Sungho Lee, Marco A. Martínez Ramírez, Wei-Hsiang Liao, Stefan Uhlich, Giorgio Fabbro, Kyogu Lee, Yuki Mitsufuji
Searching For Music Mixing Graphs: A Pruning Approach. CoRR (2024)
Giorgio Fabbro, Stefan Uhlich, Chieh-Hsin Lai, Woosung Choi, Marco A. Martínez Ramírez, Wei-Hsiang Liao, Igor Gadelha, Geraldo Ramos, Eddie Hsu, Hugo Rodrigues, Fabian-Robert Stöter, Alexandre Défossez, Yi Luo, Jianwei Yu, Dipam Chakraborty, Sharada P. Mohanty, Roman A. Solovyev, Alexander L. Stempkovskiy, Tatiana Habruseva, Nabarun Goswami, Tatsuya Harada, Minseok Kim, Jun Hyung Lee, Yuanliang Dong, Xinran Zhang, Jiafeng Liu, Yuki Mitsufuji
The Sound Demixing Challenge 2023 - Music Demixing Track. Trans. Int. Soc. Music. Inf. Retr. 7 (1) (2024)
Bac Nguyen, Stefan Uhlich, Fabien Cardinaux
Improving Self-Supervised Learning for Audio Representations by Feature Diversity and Decorrelation. ICASSP (2023)
Bac Nguyen, Stefan Uhlich, Fabien Cardinaux
Improving Self-Supervised Learning for Audio Representations by Feature Diversity and Decorrelation. CoRR (2023)
Giorgio Fabbro, Stefan Uhlich, Chieh-Hsin Lai, Woosung Choi, Marco A. Martínez Ramírez, Wei-Hsiang Liao, Igor Gadelha, Geraldo Ramos, Eddie Hsu, Hugo Rodrigues, Fabian-Robert Stöter, Alexandre Défossez, Yi Luo, Jianwei Yu, Dipam Chakraborty, Sharada P. Mohanty, Roman A. Solovyev, Alexander L. Stempkovskiy, Tatiana Habruseva, Nabarun Goswami, Tatsuya Harada, Minseok Kim, Jun Hyung Lee, Yuanliang Dong, Xinran Zhang, Jiafeng Liu, Yuki Mitsufuji
The Sound Demixing Challenge 2023 - Music Demixing Track. CoRR (2023)
Yassir Bendou, Vincent Gripon, Bastien Pasdeloup, Giulia Lioi, Lukas Mauch, Stefan Uhlich, Fabien Cardinaux, Ghouthi Boukli Hacene, Javier Alonso García
A Statistical Model for Predicting Generalization in Few-Shot Classification. EUSIPCO (2023)
Bac Nguyen, Fabien Cardinaux, Stefan Uhlich
Autotts: End-to-End Text-to-Speech Synthesis Through Differentiable Duration Modeling. ICASSP (2023)
Ryosuke Sawata, Naoya Takahashi, Stefan Uhlich, Shusuke Takahashi, Yuki Mitsufuji
The Whole Is Greater than the Sum of Its Parts: Improving DNN-based Music Source Separation. CoRR (2023)
Stefan Uhlich, Giorgio Fabbro, Masato Hirano, Shusuke Takahashi, Gordon Wichern, Jonathan Le Roux, Dipam Chakraborty, Sharada P. Mohanty, Kai Li, Yi Luo, Jianwei Yu, Rongzhi Gu, Roman A. Solovyev, Alexander L. Stempkovskiy, Tatiana Habruseva, Mikhail Sukhovei, Yuki Mitsufuji
The Sound Demixing Challenge 2023 - Cinematic Demixing Track. CoRR (2023)
Junghyun Koo, Marco A. Martínez Ramírez, Wei-Hsiang Liao, Stefan Uhlich, Kyogu Lee, Yuki Mitsufuji
Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects. ICASSP (2023)
Marco A. Martínez Ramírez, Wei-Hsiang Liao, Chihiro Nagashima, Giorgio Fabbro, Stefan Uhlich, Yuki Mitsufuji
Automatic music mixing with deep learning and out-of-domain data. ISMIR (2022)
Ali Aroudi, Stefan Uhlich, Marc Ferras Font
TRUNet: Transformer-Recurrent-U Network for Multi-channel Reverberant Sound Source Separation. INTERSPEECH (2022)
Junghyun Koo, Marco A. Martínez Ramírez, Wei-Hsiang Liao, Stefan Uhlich, Kyogu Lee, Yuki Mitsufuji
Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects. CoRR (2022)
Johannes Imort, Giorgio Fabbro, Marco A. Martínez Ramírez, Stefan Uhlich, Yuichiro Koyama, Yuki Mitsufuji
Removing Distortion Effects in Music Using Deep Neural Networks. CoRR (2022)
Marco A. Martínez Ramírez, Wei-Hsiang Liao, Giorgio Fabbro, Stefan Uhlich, Chihiro Nagashima, Yuki Mitsufuji
Automatic music mixing with deep learning and out-of-domain data. CoRR (2022)
Johannes Imort, Giorgio Fabbro, Marco A. Martínez Ramírez, Stefan Uhlich, Yuichiro Koyama, Yuki Mitsufuji
Distortion Audio Effects: Learning How to Recover the Clean Signal. ISMIR (2022)
Yassir Bendou, Vincent Gripon, Bastien Pasdeloup, Lukas Mauch, Stefan Uhlich, Fabien Cardinaux, Ghouthi Boukli Hacene, Javier Alonso García
A Statistical Model for Predicting Generalization in Few-Shot Classification. CoRR (2022)
Yuichiro Koyama, Naoki Murata, Stefan Uhlich, Giorgio Fabbro, Shusuke Takahashi, Yuki Mitsufuji
Music Source Separation With Deep Equilibrium Models. ICASSP (2022)
Bac Nguyen Cong, Fabien Cardinaux, Stefan Uhlich
Differentiable Duration Modeling for End-to-End Text-to-Speech. CoRR (2022)
Ryosuke Sawata, Stefan Uhlich, Shusuke Takahashi, Yuki Mitsufuji
All For One And One For All: Improving Music Separation By Bridging Networks. ICASSP (2021)
Yuki Mitsufuji, Giorgio Fabbro, Stefan Uhlich, Fabian-Robert Stöter
Music Demixing Challenge at ISMIR 2021. CoRR (2021)
Yuichiro Koyama, Naoki Murata, Stefan Uhlich, Giorgio Fabbro, Shusuke Takahashi, Yuki Mitsufuji
Music Source Separation with Deep Equilibrium Models. CoRR (2021)
Ghouthi Boukli Hacene, Lukas Mauch, Stefan Uhlich, Fabien Cardinaux
DNN Quantization with Attention. CoRR (2021)
Ali Aroudi, Stefan Uhlich, Marc Ferras Font
TRUNet: Transformer-Recurrent-U Network for Multi-channel Reverberant Sound Source Separation. CoRR (2021)
Koichi Saito, Stefan Uhlich, Giorgio Fabbro, Yuki Mitsufuji
Training Speech Enhancement Systems with Noisy Speech Datasets. CoRR (2021)
Mohammad Asif Khan, Fabien Cardinaux, Stefan Uhlich, Marc Ferras, Asja Fischer
Unsupervised Cross-Domain Speech-to-Speech Conversion with Time-Frequency Consistency. CoRR (2020)
Fabien Cardinaux, Stefan Uhlich, Kazuki Yoshiyama, Javier Alonso García, Lukas Mauch, Stephen Tiedemann, Thomas Kemp, Akira Nakamura
Iteratively Training Look-Up Tables for Network Quantization. IEEE J. Sel. Top. Signal Process. 14 (4) (2020)
Yuki Mitsufuji, Stefan Uhlich, Norihiro Takamune, Daichi Kitamura, Shoichi Koyama, Hiroshi Saruwatari
Multichannel Non-Negative Matrix Factorization Using Banded Spatial Covariance Matrices in Wavenumber Domain. IEEE ACM Trans. Audio Speech Lang. Process. 28 (2020)
Ryosuke Sawata, Stefan Uhlich, Shusuke Takahashi, Yuki Mitsufuji
All for One and One for All: Improving Music Separation by Bridging Networks. CoRR (2020)
Stefan Uhlich, Lukas Mauch, Fabien Cardinaux, Kazuki Yoshiyama, Javier Alonso García, Stephen Tiedemann, Thomas Kemp, Akira Nakamura
Mixed Precision DNNs: All you need is a good parametrization. ICLR (2020)
Yuichiro Koyama, Tyler Vuong, Stefan Uhlich, Bhiksha Raj
Exploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks. CoRR (2020)
Fabien Cardinaux, Stefan Uhlich, Kazuki Yoshiyama, Javier Alonso García, Lukas Mauch, Stephen Tiedemann, Thomas Kemp, Akira Nakamura
Iteratively Training Look-Up Tables for Network Quantization. CoRR (2019)
Stefan Uhlich, Lukas Mauch, Kazuki Yoshiyama, Fabien Cardinaux, Javier Alonso García, Stephen Tiedemann, Thomas Kemp, Akira Nakamura
Differentiable Quantization of Deep Neural Networks. CoRR (2019)
Cyril Cadoux, Stefan Uhlich, Marc Ferras, Yuki Mitsufuji
Closing the Training/Inference Gap for Deep Attractor Networks. CoRR (2019)
Fabian-Robert Stöter, Stefan Uhlich, Antoine Liutkus, Yuki Mitsufuji
Open-Unmix - A Reference Implementation for Music Source Separation. J. Open Source Softw. 4 (41) (2019)
Joachim Muth, Stefan Uhlich, Nathanaël Perraudin, Thomas Kemp, Fabien Cardinaux, Yuki Mitsufuji
Improving DNN-based Music Source Separation using Phase Features. CoRR (2018)
Fabien Cardinaux, Stefan Uhlich, Kazuki Yoshiyama, Javier Alonso García, Stephen Tiedemann, Thomas Kemp, Akira Nakamura
Iteratively Training Look-Up Tables for Network Quantization. CoRR (2018)
Stefan Uhlich, Marcello Porcu, Franck Giron, Michael Enenkl, Thomas Kemp, Naoya Takahashi, Yuki Mitsufuji
Improving music source separation based on deep neural networks through data augmentation and network blending. ICASSP (2017)
Stefan Uhlich, Franck Giron, Yuki Mitsufuji
Deep neural network based instrument extraction from music. ICASSP (2015)
Stefan Uhlich
Bayes Risk Reduction of Estimators Using Artificial Observation Noise. IEEE Trans. Signal Process. 63 (20) (2015)
Xin Guo, Stefan Uhlich, Yuki Mitsufuji
NMF-based blind source separation using a linear predictive coding error clustering criterion. ICASSP (2015)
Stefan Uhlich
Computing Jacobian and Hessian of Estimators and Their Application to Risk Approximation. IEEE Signal Process. Lett. 21 (4) (2014)
Stefan Uhlich, Bin Yang
Bayesian Estimation for Nonstandard Loss Functions Using a Parametric Family of Estimators. IEEE Trans. Signal Process. 60 (3) (2012)
Stefan Uhlich, Bin Yang
Recursive estimation of room impulse responses with energy conservation constraints. ICASSP (2011)
Stefan Uhlich, Bin Yang
A parametric family of Bayesian estimators for non-standard loss functions. EUSIPCO (2010)
Stefan Uhlich, Bin Yang
Efficient recursive estimators for a linear, time-varying Gaussian model with general constraints. IEEE Trans. Signal Process. 58 (9) (2010)
Stefan Uhlich, Bin Yang
MMSE estimation in a linear signal model with ellipsoidal constraints. ICASSP (2009)
Rainer Blind, Stefan Uhlich, Bin Yang, Frank Allgöwer
Robustification and optimization of a Kalman filter with measurement loss using linear precoding. ACC (2009)
Stefan Uhlich, Bin Yang
A generalized optimal correlating transform for multiple description coding and its theoretical analysis. ICASSP (2008)

Stefan Uhlich.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Stefan Uhlich