Fusing Audio and Metadata Embeddings Improves Language-based Audio Retrieval von Primus, Paul, Widmer, Gerhard

Volltext bestellen

Improved Zero-Shot Audio Tagging & Classification with Patchout Spectrogram Transformers von Primus, Paul, Widmer, Gerhard

Volltext bestellen

Improving Natural-Language-based Audio Retrieval with Transfer Learning and Audio & Text Augmentations von Primus, Paul, Widmer, Gerhard

Volltext bestellen

On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers von and, Paul Primus, Widmer, Gerhard

Volltext bestellen

Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval von Primus, Paul, Schmid, Florian, Widmer, Gerhard

Volltext bestellen

Fusing Audio and Metadata Embeddings Improves Language-based Audio Retrieval von Primus, Paul, Widmer, Gerhard

Volltext

Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets von Primus, Paul, Koutini, Khaled, Widmer, Gerhard

Volltext bestellen

Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining von Greif, Jonathan, Schmid, Florian, Primus, Paul, Widmer, Gerhard

Volltext bestellen

Multi-Iteration Multi-Stage Fine-Tuning of Transformers for Sound Event Detection with Heterogeneous Datasets von Schmid, Florian, Primus, Paul, Morocutti, Tobias, Greif, Jonathan, Widmer, Gerhard

Volltext bestellen

Improving Audio Spectrogram Transformers for Sound Event Detection Through Multi-Stage Training von Schmid, Florian, Primus, Paul, Morocutti, Tobias, Greif, Jonathan, Widmer, Gerhard

Volltext bestellen

Improving Natural-Language-based Audio Retrieval with Transfer Learning and Audio & Text Augmentations von Primus, Paul, Widmer, Gerhard

Volltext

Improved Zero-Shot Audio Tagging & Classification with Patchout Spectrogram Transformers von Primus, Paul, Widmer, Gerhard

Volltext

Effective Pre-Training of Audio Transformers for Sound Event Detection von Schmid, Florian, Morocutti, Tobias, Foscarin, Francesco, Schlüter, Jan, Primus, Paul, Widmer, Gerhard

Volltext bestellen

On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers von Paul Primus and, Widmer, Gerhard

Volltext

Data-Efficient Low-Complexity Acoustic Scene Classification in the DCASE 2024 Challenge von Schmid, Florian, Primus, Paul, Heittola, Toni, Mesaros, Annamaria, Martín-Morató, Irene, Koutini, Khaled, Widmer, Gerhard

Volltext bestellen

Estimated Audio-Caption Correspondences Improve Language-Based Audio Retrieval von Primus, Paul, Schmid, Florian, Widmer, Gerhard

Volltext

Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets von Primus, Paul, Koutini, Khaled, Widmer, Gerhard

Volltext

Anomalous Sound Detection as a Simple Binary Classification Problem with Careful Selection of Proxy Outlier Examples von Primus, Paul, Haunschmid, Verena, Praher, Patrick, Widmer, Gerhard

Volltext bestellen

Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining von Greif, Jonathan, Schmid, Florian, Primus, Paul, Widmer, Gerhard

Volltext

Multi-Iteration Multi-Stage Fine-Tuning of Transformers for Sound Event Detection with Heterogeneous Datasets von Schmid, Florian, Primus, Paul, Morocutti, Tobias, Greif, Jonathan, Widmer, Gerhard

Volltext