Pre-training Audio Embeddings

Changhong Wang, Gaël Richard, Brian McFeeZenodo 2023 · DOI · OpenAlex

Abstract

Pre-trained audio embeddings (VGGish, OpenL3, YAMNet) of IRMAS and OpenMIC-2018 datasets, released in the following paper: Changhong Wang, Brian McFee, and Gaël Richard. "<strong>Transfer Learning and Bias Correction with Pre-trained Audio Embeddings</strong>". <em>Proceedings of the International Society for Music Information Retrieval (ISMIR) Conference</em>, 2023.
BibTeX
@inproceedings{wang2023pre,
  author = {Changhong Wang and Gaël Richard and Brian McFee},
  title = {{Pre-training Audio Embeddings}},
  booktitle = {Zenodo},
  year = {2023},
  doi = {10.5281/zenodo.8126907},
}

Loading related content...

Figure