4 Publications
2025 | Conference Paper | LibreCat-ID: 62163
Werning, Alexander, and Reinhold Häb-Umbach. “A Fully Zero-Shot Approach to Obtaining Specialized and Compact Audio Tagging Models.” Proceedings of the 16th ITG Conference on Speech Communication, edited by Sebastian Möller et al., 2025, pp. 76–80.
LibreCat
2025 | Conference Paper | LibreCat-ID: 59900
Werning, Alexander, and Reinhold Häb-Umbach. “Distilling Efficient Audio Models Using Data Pruning with CLAP.” Proceedings of DAS|DAGA 2025, edited by Deutsche Gesellschaft für Akustik e.V. (DEGA), Berlin, 2025, 2025.
LibreCat
2024 | Report | LibreCat-ID: 57161
Werning, Alexander, and Reinhold Haeb-Umbach. UPB-NT Submission to DCASE24: Dataset Pruning for Targeted Knowledge Distillation. 2024.
LibreCat
2024 | Conference Paper | LibreCat-ID: 57160
Werning, Alexander, and Reinhold Haeb-Umbach. “Target-Specific Dataset Pruning for Compression of Audio Tagging Models.” 32nd European Signal Processing Conference (EUSIPCO 2024), 2024.
LibreCat
| Files available
4 Publications
2025 | Conference Paper | LibreCat-ID: 62163
Werning, Alexander, and Reinhold Häb-Umbach. “A Fully Zero-Shot Approach to Obtaining Specialized and Compact Audio Tagging Models.” Proceedings of the 16th ITG Conference on Speech Communication, edited by Sebastian Möller et al., 2025, pp. 76–80.
LibreCat
2025 | Conference Paper | LibreCat-ID: 59900
Werning, Alexander, and Reinhold Häb-Umbach. “Distilling Efficient Audio Models Using Data Pruning with CLAP.” Proceedings of DAS|DAGA 2025, edited by Deutsche Gesellschaft für Akustik e.V. (DEGA), Berlin, 2025, 2025.
LibreCat
2024 | Report | LibreCat-ID: 57161
Werning, Alexander, and Reinhold Haeb-Umbach. UPB-NT Submission to DCASE24: Dataset Pruning for Targeted Knowledge Distillation. 2024.
LibreCat
2024 | Conference Paper | LibreCat-ID: 57160
Werning, Alexander, and Reinhold Haeb-Umbach. “Target-Specific Dataset Pruning for Compression of Audio Tagging Models.” 32nd European Signal Processing Conference (EUSIPCO 2024), 2024.
LibreCat
| Files available