TGFC Lifestyle - Powered by Discuz! Board

标题: 有没有把歌里面只保留音乐去掉人声的软件？ [打印本页]

作者: 马甲爵 时间: 2018-2-2 09:45 标题: 有没有把歌里面只保留音乐去掉人声的软件？

posted by wap, platform: Android
求推荐

作者: lovecf4444 时间: 2018-2-2 09:49

audio audition,如果原曲是双声道，就很方便，如果是压在一个音轨上就要手工抠了。

作者: dreamboyg 时间: 2018-2-2 10:53

能有软件这么牛？
这又不是两个音轨的
音乐和人声不是混在一起的吗？

作者: 加勒比海带 时间: 2018-2-2 11:13

posted by wap, platform: iPhone
一个音轨几乎无法处理我试过

作者: arex 时间: 2018-2-2 11:24

posted by wap, platform: Android
试过很多方法，处理过效果也很差了

作者: jjx01 时间: 2018-2-2 12:01

audition提取中置声道，然而效果很差

找人扒谱，一首2～3000

作者: b0207191 时间: 2018-2-2 12:52

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

作者: arex 时间: 2018-2-2 13:35

posted by wap, platform: Android
试过很多方法，处理过效果也很差了

作者: 000月 时间: 2018-2-2 18:56

posted by wap, platform: iPhone
AA直接人声消除，看曲子，有些扒完还能听，有些直接就不剩啥了

作者: mimicry 时间: 2018-2-2 19:31

posted by wap, platform: iPhone
等人工智能解决吧

作者: b0207191 时间: 2018-2-2 19:40

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 ❤

作者: b0207191 时间: 2018-2-2 19:43

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

作者: beterhans 时间: 2018-2-3 09:50

posted by wap, platform: 锤子坚果
目前不存在这种软件
一般都是左右声道抵消相同波形实现效果极差

作者: 马甲爵 时间: 2018-2-3 12:47

posted by wap, platform: Android
谢谢

作者: beterhans 时间: 2018-2-6 07:48

posted by wap, platform: iPhone

引用:

原帖由 @b0207191  于 2018-2-2 19:40 发表
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 ❤

这东西你用过吗？

作者: beterhans 时间: 2018-2-6 09:58

尝试了那个高达上的 python 脚本
总是提示却这却拿
跑不起来

hans@VUbuntu:/media/sf_Downloads$ python3 /home/hans/source/acapellabot/acapellabot.py org.mp3
/usr/local/lib/python3.5/dist-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  from ._conv import register_converters as _register_converters
Using Theano backend.
WARNING (theano.tensor.blas): Using NumPy C-API based implementation for BLAS functions.
Model has 668225 params
Weights provided; performing inference on ['org.mp3']...
Loading weights
Traceback (most recent call last):
  File "/home/hans/source/acapellabot/acapellabot.py", line 145, in <module>
acapellabot.loadWeights(args.weights)
  File "/home/hans/source/acapellabot/acapellabot.py", line 88, in loadWeights
self.model.load_weights(path)
  File "/usr/local/lib/python3.5/dist-packages/keras/engine/topology.py", line 2638, in load_weights
f = h5py.File(filepath, mode='r')
  File "/usr/local/lib/python3.5/dist-packages/h5py/_hl/files.py", line 269, in __init__
fid = make_fid(name, mode, userblock_size, fapl, swmr=swmr)
  File "/usr/local/lib/python3.5/dist-packages/h5py/_hl/files.py", line 99, in make_fid
fid = h5f.open(name, flags, fapl=fapl)
  File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
  File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
  File "h5py/h5f.pyx", line 78, in h5py.h5f.open
OSError: Unable to open file (unable to open file: name = 'weights.h5', errno = 2, error message = 'No such file or directory', flags = 0, o_flags = 0)

欢迎光临 TGFC Lifestyle (http://club.tgfcer.com/)