Augment, Drop & Swap: Improving Diversity in LLM Captions for Efficient Music-Text Representation Learning.

Ilaria Manco|Justin Salamon|Oriol Nieto


Anthology ID:DBLP:conf/ismir/MancoSN24
Volume:Proceedings of the 25th International Society for Music Information Retrieval Conference, ISMIR 2024, San Francisco, California, USA and Online, November 10-14, 2024.
Year:2024
Venue:International Society for Music Information Retrieval Conference (ISMIR)
Pages:938-945
URL:https://doi.org/10.5281/ZENODO.14877485
DOI:https://doi.org/10.5281/ZENODO.14877485
DBLP:conf/ismir/MancoSN24
BibTeX:
@inproceedings{manco-2024-augment, author = {Ilaria Manco and Justin Salamon and Oriol Nieto}, editor = {Blair Kaneshiro and Gautham J. Mysore and Oriol Nieto and Chris Donahue and Cheng-Zhi Anna Huang and Jin Ha Lee and Brian McFee and Matthew C. McCallum}, title = {{Augment, Drop & Swap: Improving Diversity in LLM Captions for Efficient Music-Text Representation Learning}}, booktitle = {{Proceedings of the 25th International Society for Music Information Retrieval Conference, ISMIR 2024, San Francisco, California, USA and Online, November 10-14, 2024}}, pages = {938--945}, year = {2024}, url = {https://doi.org/10.5281/ZENODO.14877485}, doi = {https://doi.org/10.5281/ZENODO.14877485} }