3 Dokumente gefunden

Semi-supervised and transfer learning for few-shot audio classification

Deep Learning hat zu erheblichen Fortschritten in der Audioanalyse geführt, doch die Abhängigkeit von großen, gelabelten Datensätzen stellt in spezialisierten Bereichen wie der Musikwissenschaft und der industriellen Qualitätskontrolle ein wesentliches Hindernis dar. Diese Arbeit untersucht Transfer…

How reliable are posterior class probabilities in automatic music classification?

Music classification algorithms use signal processing and machine learning approaches to extract and enrich metadata for audio recordings in music archives. Common tasks include music genre classification, where each song is assigned a single label (such as Rock, Pop, or Jazz), and musical instrument…
New York, NY: The Association for Computing Machinery, 2023-10-11

Improving semi-supervised learning for audio classification with FixMatch

Including unlabeled data in the training process of neural networks using Semi-Supervised Learning (SSL) has shown impressive results in the image domain, where state-of-the-art results were obtained with only a fraction of the labeled data. The commonality between recent SSL methods is that they strongly…
Basel: MDPI, 2021-07-28