Singing voice separation: a study on training data — mentioned by ikhatri

Wed, 07 Jun 2023 22:49:54 GMT

Yup! It's a U-Net style convolutional neural network that runs on the spectrograms. There's a short 2 page abstract here: https://archives.ismir.net/ismir2019/latebreaking/000036.pdf and they cite this prior work as where they got the architecture from: https://arxiv.org/abs/1906.02618

Paper and discussion history. A mention is not an endorsement.

Singing voice separation: a study on training data · HackerPapers discussions

Singing voice separation: a study on training data — mentioned by ikhatri