| The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification. K Koutini, H Eghbal-zadeh, M Dorfer, G Widmer Proceedings of the European Signal Processing Conference (EUSIPCO), 2019 | 91 | 2019 |
| Acoustic Scene Classification and Audio Tagging with Receptive-Field-Regularized CNNs K Koutini, H Eghbal-zadeh, G Widmer Proceedings of the Detection and Classification of Acoustic Scenes and …, 2019 | 52 | 2019 |
| Efficient Training of Audio Transformers with Patchout K Koutini, J Schlüter, H Eghbal-zadeh, G Widmer Interspeech 2022, 23nd Annual Conference of the International Speech …, 2021 | 50 | 2021 |
| Receptive-field-regularized CNN variants for acoustic scene classification K Koutini, H Eghbal-zadeh, G Widmer Proceedings of the Detection and Classification of Acoustic Scenes and …, 2019 | 35 | 2019 |
| CP-JKU submissions to DCASE’20: Low-complexity cross-device acoustic scene classification with rf-regularized CNNs K Koutini, F Henkel, H Eghbal-zadeh, G Widmer Tech. Rep., DCASE2020 Challenge, 2020 | 29 | 2020 |
| Classifying short acoustic scenes with I-vectors and CNNs: Challenges and optimisations for the 2017 DCASE ASC task B Lehner, H Eghbal-Zadeh, M Dorfer, F Korzeniowski, K Koutini, ... IEEE AASP Challenge on Detection and Classification of Acoustic Scen and …, 2017 | 28 | 2017 |
| Receptive field regularization techniques for audio classification and tagging with deep convolutional neural networks K Koutini, H Eghbal-zadeh, G Widmer IEEE/ACM Transactions on Audio, Speech, and Language Processing 29, 1987-2000, 2021 | 25 | 2021 |
| Iterative knowledge distillation in r-cnns for weakly-labeled semi-supervised sound event detection K Koutini, H Eghbal-zadeh, G Widmer Detection and Classification of Acoustic Scenes and Events (DCASE) 2018 …, 2018 | 21 | 2018 |
| Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs K Koutini, S Chowdhury, V Haunschmid, H Eghbal-zadeh, G Widmer Proceedings of the MediaEval 2019 Workshop, Sophia Antipolis, France, 27-30 …, 2019 | 20 | 2019 |
| Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification P Primus, H Eghbal-zadeh, D Eitelsebner, K Koutini, A Arzt, G Widmer Proceedings of the Detection and Classification of Acoustic Scenes and …, 2019 | 19 | 2019 |
| Acoustic scene classification with reject option based on resnets B Lehner, K Koutini, C Schwarzlmüller, T Gallien, G Widmer Proceedings of the Detection and Classification of Acoustic Scenes and …, 2019 | 14 | 2019 |
| Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping K Koutini, F Henkel, H Eghbal-zadeh, G Widmer Proceedings of the Detection and Classification of Acoustic Scenes and …, 2020 | 12 | 2020 |
| CPJKU SUBMISSION TO DCASE21: Cross-device audio scene classification with wide sparse frequency-damped CNNs K Koutini, J Schlüter, G Widmer DCASE2021 Challenge, Tech. Rep., 2021 | 11 | 2021 |
| Acoustic scene classification and audio tagging with receptive-fieldregularized CNNs H Eghbal-zadeh, K Koutini, G Widmer Tech. Rep., DCASE 2019 Challenge, 2019 | 8 | 2019 |
| On Data Augmentation and Adversarial Risk: An Empirical Analysis H Eghbal-zadeh, K Koutini, P Primus, V Haunschmid, M Lewandowski, ... arXiv preprint arXiv:2007.02650, 2020 | 7 | 2020 |
| MediaEval 2017 AcousticBrainz Genre Task: Multilayer Perceptron Approach. K Koutini, A Imenina, M Dorfer, A Gruber, M Schedl MediaEval, 2017 | 5 | 2017 |
| CP-JKU SUBMISSION TO DCASE22: DISTILLING KNOWLEDGE FOR LOW-COMPLEXITY CONVOLUTIONAL NEURAL NETWORKS FROM A PATCHOUT AUDIO TRANSFORMER F Schmid, S Masoudian, K Koutini, G Widmer DCASE2022 Challenge, Tech. Rep, 2022 | 4 | 2022 |
| Receptive-Field Regularized CNNs for Music Classification and Tagging K Koutini, H Eghbal-Zadeh, V Haunschmid, P Primus, S Chowdhury, ... arXiv preprint arXiv:2007.13503, 2020 | 4 | 2020 |
| Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation F Schmid, K Koutini, G Widmer arXiv preprint arXiv:2211.04772, 2022 | 3 | 2022 |
| Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers K Koutini, S Masoudian, F Schmid, H Eghbal-zadeh, J Schlüter, G Widmer HEAR: Holistic Evaluation of Audio Representations, Proceedings of Machine …, 2022 | 2 | 2022 |
Gerhard WidmerProfessor of Computer Science, Johannes Kepler University LinzVerified email at jku.at
