search

andabi / music-source-separation

Deep neural networks for separating singing voice from music written in TensorFlow
796 stars 149 forks source link

speech enhancement? #3

Open ghost opened 7 years ago

ghost commented 7 years ago

Will this framework work for speech enhancement task with custom dataset? If I have stereo wav files in same format where left channel is background noise and right channel is clean speech, can it work?

andabi commented 7 years ago

@dankorg Actually I didn't try to target speech denoising task with the same model. But I think it would work with the speech denoising task as well. I expect the model is extendable to all kinds of separation task if having appropriate dataset ;)