Quantize & Factorize: A fast yet effective unsupervised audio representation without deep learning.

Jaehun Kim|Matthew C. McCallum|Andreas F. Ehmann


Anthology ID:DBLP:conf/ismir/KimME25
Volume:Proceedings of the 26th International Society for Music Information Retrieval Conference, ISMIR 2025, Daejeon, South Korea, September 21-25, 2025
Year:2025
Venue:International Society for Music Information Retrieval Conference (ISMIR)
Pages:787-796
URL:https://doi.org/10.5281/ZENODO.17811485
DOI:https://doi.org/10.5281/ZENODO.17811485
DBLP:conf/ismir/KimME25
BibTeX:
@inproceedings{kim-2025-quantize, author = {Jaehun Kim and Matthew C. McCallum and Andreas F. Ehmann}, editor = {Juhan Nam and Dasaem Jeong and Keunwoo Choi and Li Su and Magdalena Fuentes and Tomoyasu Nakano and Xiao Hu and Hao-Wen Dong}, title = {{Quantize & Factorize: A fast yet effective unsupervised audio representation without deep learning}}, booktitle = {{Proceedings of the 26th International Society for Music Information Retrieval Conference, ISMIR 2025, Daejeon, South Korea, September 21-25, 2025}}, pages = {787--796}, year = {2025}, url = {https://doi.org/10.5281/ZENODO.17811485}, doi = {https://doi.org/10.5281/ZENODO.17811485} }