http://wiki.audacityteam.org/wik ... 4%E4%BA%BA%E8%81%B2

引用:

原帖由 mimicry 于 2018-2-2 19:31 发表
posted by wap, platform: iPhone
等人工智能解决吧

有人在尝试了
https://github.com/madebyollin/acapellabot
AcapellaBot

Isolating vocals from music with a Convolutional Neural Network. Blog post is here.

To Use:

    Download the repo
    Install the latest versions of Theano, Keras, librosa, and h5py on Python 3.
    Set your dimension ordering to tf in ~/keras/keras.json:

    {
        "backend": "theano",
        "image_dim_ordering": "tf"
    }

    Run python acapellabot.py song.mp3

Enjoy ❤

https://arxiv.org/ftp/arxiv/papers/1504/1504.04658.pdf