Stefan Uhlich
Stefan Uhlich
Sony Europe B.V., ZNL Deutschland
Geverifieerd e-mailadres voor lss.uni-stuttgart.de
Geciteerd door
Geciteerd door
Improving music source separation based on deep neural networks through data augmentation and network blending
S Uhlich, M Porcu, F Giron, M Enenkl, T Kemp, N Takahashi, Y Mitsufuji
International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017
Open-unmix-a reference implementation for music source separation
FR Stöter, S Uhlich, A Liutkus, Y Mitsufuji
Journal of Open Source Software 4 (41), 1667, 2019
Deep neural network based instrument extraction from music
S Uhlich, F Giron, Y Mitsufuji
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
Mixed precision DNNs: All you need is a good parametrization
S Uhlich, L Mauch, F Cardinaux, K Yoshiyama, JA García, S Tiedemann, ...
ICLR 2020, 2020
Exploring the best loss function for DNN-based low-latency speech enhancement with temporal convolutional networks
Y Koyama, T Vuong, S Uhlich, B Raj
arXiv preprint arXiv:2005.11611, 2020
Music demixing challenge 2021
Y Mitsufuji, G Fabbro, S Uhlich, FR Stöter
arXiv preprint arXiv:2108.13559, 2021
All for one and one for all: Improving music separation by bridging networks
R Sawata, S Uhlich, S Takahashi, Y Mitsufuji
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
Multidimensional localization of multiple sound sources using frequency domain ICA and an extended state coherence transform
B Loesch, S Uhlich, B Yang
2009 IEEE/SP 15th Workshop on Statistical Signal Processing, 677-680, 2009
Bayes risk reduction of estimators using artificial observation noise
S Uhlich
IEEE Transactions on Signal Processing 63 (20), 5535-5545, 2015
Method, system and artificial neural network
F Cardinaux, M Enenkl, F Giron, T Kemp, S Uhlich
US Patent 10,564,923, 2020
Improving DNN-based Music Source Separation using Phase Features
J Muth, S Uhlich, N Perraudin, T Kemp, F Cardinaux, Y Mitsufuji
Joint Workshop on Machine Learning for Music at ICML, IJCAI/ECAI and AAMAS, 2018
Iteratively training look-up tables for network quantization
F Cardinaux, S Uhlich, K Yoshiyama, JA García, L Mauch, S Tiedemann, ...
IEEE Journal of Selected Topics in Signal Processing 14 (4), 860-870, 2020
Multichannel non-negative matrix factorization using banded spatial covariance matrices in wavenumber domain
Y Mitsufuji, S Uhlich, N Takamune, D Kitamura, S Koyama, H Saruwatari
IEEE/ACM Transactions on Audio, Speech, and Language Processing 28, 49-60, 2019
Signal processing unit employing a blind channel estimation algorithm and method of operating a receiver apparatus
B Eitel, J Zinsser, RA Salem, S Uhlich
US Patent 9,401,826, 2016
Robustification and optimization of a Kalman filter with measurement loss using linear precoding
R Blind, S Uhlich, B Yang, F Allgower
2009 American Control Conference, 2222-2227, 2009
NMF-based blind source separation using a linear predictive coding error clustering criterion
X Guo, S Uhlich, Y Mitsufuji
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
Open-unmix for speech enhancement (UMX SE)
S Uhlich, Y Mitsufuji
May, 2020
Bayesian estimation for nonstandard loss functions using a parametric family of estimators
S Uhlich, B Yang
IEEE transactions on signal processing 60 (3), 1022-1031, 2011
MMSE estimation in a linear signal model with ellipsoidal constraints
S Uhlich, B Yang
2009 IEEE International Conference on Acoustics, Speech and Signal …, 2009
Training speech enhancement systems with noisy speech datasets
K Saito, S Uhlich, G Fabbro, Y Mitsufuji
arXiv preprint arXiv:2105.12315, 2021
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20