Khaled Koutini

37 papers A 1Misc 1Journal 23Unranked 12

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Creating a Good Teacher for Knowledge Distillation in Acoustic Scene Classification. CoRR Tobias Morocutti, Florian Schmid, Khaled Koutini, Gerhard Widmer
2024	J	`jnl`	Data-Efficient Low-Complexity Acoustic Scene Classification in the DCASE 2024 Challenge. CoRR Florian Schmid, Paul Primus, Toni Heittola, Annamaria Mesaros, Irene Martín-Morató, Khaled Koutini, Gerhard Widmer
2024	J	`jnl`	Dynamic Convolutional Neural Networks as Efficient Pre-Trained Audio Models. IEEE ACM Trans. Audio Speech Lang. Process. Florian Schmid, Khaled Koutini, Gerhard Widmer
2024	J	`jnl`	Rethinking data augmentation for adversarial robustness. Inf. Sci. Hamid Eghbal-zadeh, Werner Zellinger, Maura Pintor, Kathrin Grosse, Khaled Koutini, Bernhard Alois Moser, Battista Biggio, Gerhard Widmer
2023	J	`jnl`	Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets. CoRR Paul Primus, Khaled Koutini, Gerhard Widmer
2023	—	`conf`	Device-Robust Acoustic Scene Classification via Impulse Response Augmentation. EUSIPCO Tobias Morocutti, Florian Schmid, Khaled Koutini, Gerhard Widmer
2023	J	`jnl`	Device-Robust Acoustic Scene Classification via Impulse Response Augmentation. CoRR Tobias Morocutti, Florian Schmid, Khaled Koutini, Gerhard Widmer
2023	—	`conf`	Domain Information Control at Inference Time for Acoustic Scene Classification. EUSIPCO Shahed Masoudian, Khaled Koutini, Markus Schedl, Gerhard Widmer, Navid Rekabsaz
2023	J	`jnl`	Domain Information Control at Inference Time for Acoustic Scene Classification. CoRR Shahed Masoudian, Khaled Koutini, Markus Schedl, Gerhard Widmer, Navid Rekabsaz
2023	J	`jnl`	Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models. CoRR Florian Schmid, Khaled Koutini, Gerhard Widmer
2023	Misc	`conf`	Efficient Large-Scale Audio Tagging Via Transformer-to-CNN Knowledge Distillation. ICASSP Florian Schmid, Khaled Koutini, Gerhard Widmer
2023	—	`conf`	Low-Complexity Audio Embedding Extractors. EUSIPCO Florian Schmid, Khaled Koutini, Gerhard Widmer
2023	J	`jnl`	Low-Complexity Audio Embedding Extractors. CoRR Florian Schmid, Khaled Koutini, Gerhard Widmer
2022	J	`jnl`	Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation. CoRR Florian Schmid, Khaled Koutini, Gerhard Widmer
2022	A	`conf`	Efficient Training of Audio Transformers with Patchout. INTERSPEECH Khaled Koutini, Jan Schlüter, Hamid Eghbal-zadeh, Gerhard Widmer
2022	—	`conf`	Knowledge Distillation from Transformers for Low-Complexity Acoustic Scene Classification. DCASE Florian Schmid, Shahed Masoudian, Khaled Koutini, Gerhard Widmer
2022	J	`jnl`	Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers. CoRR Khaled Koutini, Shahed Masoudian, Florian Schmid, Hamid Eghbal-zadeh, Jan Schlüter, Gerhard Widmer
2021	J	`jnl`	Efficient Training of Audio Transformers with Patchout. CoRR Khaled Koutini, Jan Schlüter, Hamid Eghbal-zadeh, Gerhard Widmer
2021	—	`conf`	Learning General Audio Representations With Large-Scale Training of Patchout Audio Transformers. HEAR@NeurIPS Khaled Koutini, Shahed Masoudian, Florian Schmid, Hamid Eghbal-zadeh, Jan Schlüter, Gerhard Widmer
2021	J	`jnl`	Over-Parameterization and Generalization in Audio Classification. CoRR Khaled Koutini, Hamid Eghbal-zadeh, Florian Henkel, Jan Schlüter, Gerhard Widmer
2021	J	`jnl`	Receptive Field Regularization Techniques for Audio Classification and Tagging With Deep Convolutional Neural Networks. IEEE ACM Trans. Audio Speech Lang. Process. Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer
2021	J	`jnl`	Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks. CoRR Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer
2020	—	`conf`	Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping. DCASE Khaled Koutini, Florian Henkel, Hamid Eghbal-zadeh, Gerhard Widmer
2020	J	`jnl`	Low-Complexity Models for Acoustic Scene Classification Based on Receptive Field Regularization and Frequency Damping. CoRR Khaled Koutini, Florian Henkel, Hamid Eghbal-zadeh, Gerhard Widmer
2020	J	`jnl`	On Data Augmentation and Adversarial Risk: An Empirical Analysis. CoRR Hamid Eghbal-zadeh, Khaled Koutini, Paul Primus, Verena Haunschmid, Michal Lewandowski, Werner Zellinger, Bernhard Alois Moser, Gerhard Widmer
2020	J	`jnl`	Receptive-Field Regularized CNNs for Music Classification and Tagging. CoRR Khaled Koutini, Hamid Eghbal-zadeh, Verena Haunschmid, Paul Primus, Shreyan Chowdhury, Gerhard Widmer
2019	—	`conf`	Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs. MediaEval Khaled Koutini, Shreyan Chowdhury, Verena Haunschmid, Hamid Eghbal-zadeh, Gerhard Widmer
2019	J	`jnl`	Emotion and Theme Recognition in Music with Frequency-Aware RF-Regularized CNNs. CoRR Khaled Koutini, Shreyan Chowdhury, Verena Haunschmid, Hamid Eghbal-zadeh, Gerhard Widmer
2019	—	`conf`	Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification. DCASE Paul Primus, Hamid Eghbal-zadeh, David Eitelsebner, Khaled Koutini, Andreas Arzt, Gerhard Widmer
2019	J	`jnl`	Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification. CoRR Paul Primus, Hamid Eghbal-zadeh, David Eitelsebner, Khaled Koutini, Andreas Arzt, Gerhard Widmer
2019	—	`conf`	Receptive-Field-Regularized CNN Variants for Acoustic Scene Classification. DCASE Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer
2019	J	`jnl`	Receptive-field-regularized CNN variants for acoustic scene classification. CoRR Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer
2019	—	`conf`	The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification. EUSIPCO Khaled Koutini, Hamid Eghbal-zadeh, Matthias Dorfer, Gerhard Widmer
2019	J	`jnl`	The Receptive Field as a Regularizer in Deep Convolutional Neural Networks for Acoustic Scene Classification. CoRR Khaled Koutini, Hamid Eghbal-zadeh, Matthias Dorfer, Gerhard Widmer
2018	J	`jnl`	Deep SNP: An End-to-end Deep Neural Network with Attention-based Localization for Break-point Detection in SNP Array Genomic data. CoRR Hamid Eghbal-zadeh, Lukas Fischer, Niko Popitsch, Florian Kromp, Sabine Taschner-Mandl, Khaled Koutini, Teresa Gerber, Eva Bozsaky, Peter F. Ambros, Inge M. Ambros, Gerhard Widmer, Bernhard Alois Moser
2018	—	`conf`	Iterative knowledge distillation in R-CNNs for weakly-labeled semi-supervised sound event detection. DCASE Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer
2017	—	`conf`	MediaEval 2017 AcousticBrainz Genre Task: Multilayer Perceptron Approach. MediaEval Khaled Koutini, Alina Imenina, Matthias Dorfer, Alexander Gruber, Markus Schedl