Paul Primus

According to our database, Paul Primus authored at least 16 papers between 2019 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

On Temporal Guidance and Iterative Refinement in Audio Source Separation.

Tobias Morocutti, Jonathan Greif, Paul Primus, Florian Schmid, Gerhard Widmer

CoRR, July, 2025

TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining.

Paul Primus, Florian Schmid, Gerhard Widmer

CoRR, May, 2025

Low-Complexity Acoustic Scene Classification with Device Information in the DCASE 2025 Challenge.

Florian Schmid, Paul Primus, Toni Heittola, Annamaria Mesaros, Irene Martín-Morató, Gerhard Widmer

CoRR, May, 2025

Effective Pre-Training of Audio Transformers for Sound Event Detection.

Florian Schmid, Tobias Morocutti, Francesco Foscarin, Jan Schlüter, Paul Primus, Gerhard Widmer

Proceedings of the 2025 IEEE International Conference on Acoustics, 2025

2024

Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval.

Paul Primus, Florian Schmid, Gerhard Widmer

CoRR, 2024

Improving Audio Spectrogram Transformers for Sound Event Detection Through Multi-Stage Training.

Florian Schmid, Paul Primus, Tobias Morocutti, Jonathan Greif, Gerhard Widmer

CoRR, 2024

Data-Efficient Low-Complexity Acoustic Scene Classification in the DCASE 2024 Challenge.

Florian Schmid, Paul Primus, Toni Heittola, Annamaria Mesaros, Irene Martín-Morató, Khaled Koutini, Gerhard Widmer

CoRR, 2024

Fusing Audio and Metadata Embeddings Improves Language-Based Audio Retrieval.

Paul Primus, Gerhard Widmer

Proceedings of the 32nd European Signal Processing Conference, 2024

2023

Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets.

Paul Primus, Khaled Koutini, Gerhard Widmer

CoRR, 2023

On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers.

Paul Primus, Gerhard Widmer

Proceedings of the 31st European Signal Processing Conference, 2023

2022

Improved Zero-Shot Audio Tagging & Classification with Patchout Spectrogram Transformers.

Paul Primus, Gerhard Widmer

Proceedings of the 30th European Signal Processing Conference, 2022

Improving Natural-Language-Based Audio Retrieval with Transfer Learning and Audio & Text Augmentations.

Paul Primus, Gerhard Widmer

Proceedings of the 7th Workshop on Detection and Classification of Acoustic Scenes and Events 2022, 2022

2020

Receptive-Field Regularized CNNs for Music Classification and Tagging.

Khaled Koutini, Hamid Eghbal-Zadeh, Verena Haunschmid, Paul Primus, Shreyan Chowdhury, Gerhard Widmer

CoRR, 2020

On Data Augmentation and Adversarial Risk: An Empirical Analysis.

Hamid Eghbal-zadeh, Khaled Koutini, Paul Primus, Verena Haunschmid, Michal Lewandowski, Werner Zellinger, Bernhard Alois Moser, Gerhard Widmer

CoRR, 2020

Anomalous Sound Detection as a Simple Binary Classification Problem with Careful Selection of Proxy Outlier Examples.

Paul Primus, Verena Haunschmid, Patrick Praher, Gerhard Widmer

Proceedings of 5th the Workshop on Detection and Classification of Acoustic Scenes and Events 2020 (DCASE 2020), 2020

2019

Exploiting Parallel Audio Recordings to Enforce Device Invariance in CNN-based Acoustic Scene Classification.

Paul Primus, Hamid Eghbal-zadeh, David Eitelsebner, Khaled Koutini, Andreas Arzt, Gerhard Widmer

Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events 2019 (DCASE 2019), 2019