README.md

metadata

license: cc-by-nc-4.0
language:
  - ja
tags:
  - music
  - speech

MRDLA trained with the jaCappella corpus for vocal ensemble separation

This model was trained by Tomohiko Nakamura using the codebase). It was trained on the vocal ensemble separation task of the jaCappella dataset.

License

See the jaCappella dataset page.

Citation

See the jaCappella dataset page.

For MRDLA, please cite the following paper.

@article{TNakamura202104IEEEACMTASLP,
 author={Nakamura, Tomohiko and Kozuka, Shihori and Saruwatari, Hiroshi},
 journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
 title = {Time-domain audio source separation with neural networks based on multiresolution analysis},
 year=2021,
 doi={10.1109/TASLP.2021.3072496},
 month=apr,
 volume=29,
 pages={1687--1701},
}