Research interests

• Adversarial Machine Learning
• Representation Learning
• Learning under Distribution Mismatch
• Generative Models
• Acoustic Scene Analysis

Google Scholar

Please visit my Google Scholar, opens an external URL in a new window page.

2019

Co-author of the best student paper at DCASE 2019 workshop (Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification).
[link, opens an external URL in a new window] [report, opens an external URL in a new window]

 

Team member at the CP.JKU team achieving the 1st place at the MediaEval 2019 (Emotion and Themes Recognition in Music). [link, opens an external URL in a new window] [report, opens an external URL in a new window]

 

Team member at the CP.JKU team achieving the 3rd place at the DCASE 2019 Acoustic Event Detection and Classification Challenge Task1.B (Acoustic Scene Classification under Distribution Mismatch). [link, opens an external URL in a new window] [report, opens an external URL in a new window]

2018

Team member at the CP.JKU team achieving the 3rd place at the DCASE 2018 Acoustic Event Detection and Classification Challenge Task1.A (Acoustic Scene Classification).
[link, opens an external URL in a new window] [report, opens an external URL in a new window]

2017

Team member at the CP.JKU team achieving the 4th place at the DCASE 2017 Acoustic Event Detection and Classification Challenge Task1 (Acoustic Scene Classification).
[link, opens an external URL in a new window] [report, opens an external URL in a new window] 

2016

Leading member at the CP.JKU team achieving the 1st place at the DCASE 2016 Acoustic Event Detection and Classification Challenge Task1 (Acoustic Scene Classification).
[link, opens an external URL in a new window] [report, opens an external URL in a new window]

Bachelor thesis

Fabian Paischer: Improving Generalization of Deep Convolutional Neural Networks for Acoustic Scene Classification.

Master thesis

Khaled Koutini: Large-Scale Weakly Supervised Sound Event Detection For Smart Cars.

Paul Primus: Gradient-Based Explanations for Audio Classifiers.

William Freilinger: Ongoing.

Sebastian Zapletal: Ongoing

PhD thesis

Khaled Koutini: Ongoing.