フォロー
Matthias Zoehrer
Matthias Zoehrer
CTO Flapjack GmbH
確認したメール アドレス: flapjack-sdk.com - ホームページ
タイトル
引用先
引用先
Heart sound segmentation—An event detection approach using deep recurrent neural networks
E Messner, M Zöhrer, F Pernkopf
IEEE transactions on biomedical engineering 65 (9), 1964-1974, 2018
1152018
DNN-based speech mask estimation for eigenvector beamforming
L Pfeifenberger, M Zöhrer, F Pernkopf
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
532017
Gated recurrent networks applied to acoustic scene classification and acoustic event detection
M Zöhrer, F Pernkopf
Detection and Classification of Acoustic Scenes and Events 2016, 2016
532016
Resource-efficient neural networks for embedded systems
W Roth, G Schindler, B Klein, R Peharz, S Tschiatschek, H Fröning, ...
Journal of Machine Learning Research 25 (50), 1-51, 2024
472024
General stochastic networks for classification
M Zöhrer, F Pernkopf
Advances in Neural Information Processing Systems 27, 2014
312014
Representation learning for single-channel source separation and bandwidth extension
M Zöhrer, R Peharz, F Pernkopf
IEEE/ACM Transactions on Audio, Speech, and Language Processing 23 (12 …, 2015
272015
Eigenvector-based speech mask estimation for multi-channel speech enhancement
L Pfeifenberger, M Zöhrer, F Pernkopf
IEEE/ACM Transactions on Audio, Speech, and Language Processing 27 (12 …, 2019
242019
Multi-channel speech processing architectures for noise robust speech recognition: 3rd CHiME challenge results
L Pfeifenberger, T Schrank, M Zohrer, M Hagmüller, F Pernkopf
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
182015
Virtual Adversarial Training and Data Augmentation for Acoustic Event Detection with Gated Recurrent Neural Networks.
M Zöhrer, F Pernkopf
Interspeech, 493-497, 2017
162017
Deep complex-valued neural beamformers
L Pfeifenberger, M Zöhrer, F Pernkopf
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
142019
Acoustic Echo Cancellation with Cross-Domain Learning.
L Pfeifenberger, M Zoehrer, F Pernkopf
Interspeech, 4753-4757, 2021
132021
Manual versus automated: The challenging routine of infant vocalisation segmentation in home videos to study neuro (mal) development
FB Pokorny, R Peharz, W Roth, M Zöhrer, F Pernkopf, PB Marschik, ...
122016
Deep beamforming and data augmentation for robust speech recognition: Results of the 4th CHiME challenge
T Schrank, L Pfeifenberger, M Zöhrer, J Stahl, P Mowlaee, F Pernkopf
Proc. CHiME, 18-20, 2016
102016
Resource efficient deep eigenvector beamforming
M Zohrer, L Pfeifenberger, G Schindler, H Froning, F Pemkopf
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
82018
Eigenvector-Based Speech Mask Estimation Using Logistic Regression.
L Pfeifenberger, M Zöhrer, F Pernkopf
Interspeech, 2660-2664, 2017
82017
Single channel source separation with general stochastic networks
M Zöhrer, F Pernkopf
Fifteenth Annual Conference of the International Speech Communication …, 2014
82014
Towards efficient forward propagation on resource-constrained systems
G Schindler, M Zöhrer, F Pernkopf, H Fröning
Machine Learning and Knowledge Discovery in Databases: European Conference …, 2019
72019
Representation models in single channel source separation
M Zöhrer, F Pernkopf
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
62015
On representation learning for artificial bandwidth extension
M Zöhrer, R Peharz, F Pernkopf
Sixteenth Annual Conference of the International Speech Communication …, 2015
42015
Efficient and robust machine learning for real-world systems
F Pernkopf, W Roth, M Zoehrer, L Pfeifenberger, G Schindler, H Froening, ...
arXiv preprint arXiv:1812.02240, 2018
22018
現在システムで処理を実行できません。しばらくしてからもう一度お試しください。
論文 1–20