Research output per year
Research output per year
-
Effective Pre-Training of Audio Transformers for Sound Event Detection
Schmid, F., Morocutti, T., Foscarin, F., Schlüter, J., Primus, P. & Widmer, G., 07 Mar 2025, Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2025). 5 p.Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review
-
Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 Challenge
Schmid, F., Primus, P., Martín-Morató, I., Heittola, T., Widmer, G. & Mesaros, A., 2025, Proceedings of the 10th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2025).Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review
-
On Temporal Guidance and Iterative Refinement in Audio Source Separation
Morocutti, T., Greif, J., Primus, P., Schmid, F. & Widmer, G., 2025, Proceedings of the 10th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE2025): 30–31 October 2025, Barcelona, Spain. 5 p.Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review
-
On Temporal Guidance and Iterative Refinement in Audio Source Separation
Morocutti, T., Greif, J., Primus, P., Schmid, F. & Widmer, G., 23 Jul 2025, 5 p. (arXiv.org; no. 2507.17297).Research output: Working paper and reports › Preprint
Open Access -
TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining
Primus, P., Schmid, F. & Widmer, G., 14 Oct 2025, 2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA. 5 p.Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review
-
Adversarial Robustness in Data Augmentation
Zellinger, W. (Speaker), Koutini, K. (Speaker), Praher, V. (Speaker), Primus, P. (Speaker), Lewandowski, M. (Speaker), Widmer, G. (Speaker) & Eghbal-Zadeh, H. (Speaker)
26 Apr 2020Activity: Talk or presentation › Other talk or presentation › science-to-science
-
Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification
Primus, P. (Speaker)
25 Oct 2019Activity: Talk or presentation › Contributed talk › science-to-science