3 papers
eess.AS2023
Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets
Paul Primus, Khaled Koutini, Gerhard Widmer
This work presents a text-to-audio-retrieval system based on pre-trained text and spectrogram transformers. Our method projects recordings and textual descriptions into a shared au…
cs.SD2022
Improved Zero-Shot Audio Tagging & Classification with Patchout Spectrogram Transformers
Paul Primus, Gerhard Widmer
Standard machine learning models for tagging and classifying acoustic signals cannot handle classes that were not seen during training. Zero-Shot (ZS) learning overcomes this restr…
cs.SD2022
Improving Natural-Language-based Audio Retrieval with Transfer Learning and Audio & Text Augmentations
Paul Primus, Gerhard Widmer
The absence of large labeled datasets remains a significant challenge in many application areas of deep learning. Researchers and practitioners typically resort to transfer learnin…