Khaled Koutini

PhD student, Johannes Kepler University Linz

Joined

July 2021

Names

Khaled Koutini (Preferred)

Emails

****@jku.at (Confirmed)

****@gmail.com (Confirmed)

****@sony.com (Confirmed)

****@moises.ai (Confirmed)

Personal Links

Career & Education History

PhD student

Johannes Kepler University Linz (jku.at)

2018 – Present

MS student

Johannes Kepler University Linz (jku.at)

2016 – 2018

Undergrad student

Damascus University (damascusuniversity.edu.sy)

2010 – 2015

Advisors, Relations & Conflicts

Coworker

Yuki Mitsufuji

Present

PhD Advisor

Gerhard Widmer

2018 – 2023

Expertise

Audio tagging

Present

Audio Classification

Present

Model compression

Present

Vision Transformers

Present

Audio Transformers

Present

Audio generation

2024 – Present

Video to audio generation

2024 – Present

CNNs

2018 – 2021

Publications

Woosh - Sound Effect Generative Models
Gaëtan Hadjeres, Marc ferras, Khaled Koutini, Alexandre Bittar, Benno Weck, Thomas Hummel, Zineb Lahrici, Hakim Missoum, Joan Serrà, Yuki Mitsufuji
- OpenReview Archive Direct Upload
- Readers: Everyone
Rethinking Data Augmentation for Adversarial Robustness
Hamid Eghbalzadeh, Werner Zellinger, Maura Pintor, Kathrin Grosse, Khaled Koutini, Bernhard A. Moser, Battista Biggio, Gerhard Widmer
- 05 Dec 2023
- OpenReview Archive Direct Upload
- Readers: Everyone
Efficient Training of Audio Transformers with Patchout
Khaled Koutini, Jan Schlüter, Hamid Eghbal-zadeh, Gerhard Widmer
- 2022 (modified: 27 Dec 2022)
- INTERSPEECH 2022
- Readers: Everyone
Knowledge Distillation from Transformers for Low-Complexity Acoustic Scene Classification
Florian Schmid, Shahed Masoudian, Khaled Koutini, Gerhard Widmer
- 2022 (modified: 27 Dec 2022)
- DCASE 2022
- Readers: Everyone
Learning General Audio Representations with Large-Scale Training of Patchout Audio Transformers
Khaled Koutini, Shahed Masoudian, Florian Schmid, Hamid Eghbal-zadeh, Jan Schlüter, Gerhard Widmer
- 2022 (modified: 27 Dec 2022)
- CoRR 2022
- Readers: Everyone
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation
Florian Schmid, Khaled Koutini, Gerhard Widmer
- 2022 (modified: 27 Dec 2022)
- CoRR 2022
- Readers: Everyone
On Data Augmentation and Adversarial Risk: An Empirical Analysis
Hamid Eghbal-zadeh, Khaled Koutini, Paul Primus, Verena Haunschmid, Michal Lewandowski, Werner Zellinger, Bernhard A. Moser, Gerhard Widmer
- 03 Aug 2021 (modified: 03 Aug 2021)
- OpenReview Archive Direct Upload
- Readers: Everyone
Receptive Field Regularization Techniques for Audio Classification and Tagging With Deep Convolutional Neural Networks
Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer
- 2021 (modified: 19 Jul 2021)
- IEEE ACM Trans. Audio Speech Lang. Process. 2021
- Readers: Everyone
Receptive Field Regularization Techniques for Audio Classification and Tagging with Deep Convolutional Neural Networks
Khaled Koutini, Hamid Eghbal-zadeh, Gerhard Widmer
- 2021 (modified: 19 Jul 2021)
- CoRR 2021
- Readers: Everyone
Over-Parameterization and Generalization in Audio Classification
Khaled Koutini, Hamid Eghbal-zadeh, Florian Henkel, Jan Schlüter, Gerhard Widmer
- 2021 (modified: 30 Sept 2021)
- CoRR 2021
- Readers: Everyone

View all 23 publications

Co-Authors

View all 40 co-authors