0

I have an audio file with two speakers on 1 channel. I would like to separate the audio in 2 channels (one per speaker).

I was thinking of splitting on silences, or more complicated things like speaker diarization to i.e. to detect different speakers in an audio recording.

How would you do?

Jonas
  • 121,568
  • 97
  • 310
  • 388
Lucas
  • 1
  • 1
  • 1
    It's not a trivial problem. What about trying some of the open source tools mentioned in the Wikipedia article? If you want to roll your own, you need a solid background of information theory, statistical signal processing etc. – Jussi Nurminen Apr 28 '22 at 08:57
  • Please edit the question to limit it to a specific problem with enough detail to identify an adequate answer. – Community Apr 28 '22 at 19:26
  • Seems to be a complicated speech signal processing problem, specified as [blind source seperation](https://en.wikipedia.org/wiki/Signal_separation). Traditional methods include PCA/ICA and NMF. Modern method introduces neural network. – ZR Han Apr 29 '22 at 06:25

0 Answers0