Using ParallelWaveGan instead of Wavenet about speechsplit

[auspicious3000]

Yes, it is possible. You at least need to retrain one of the models to make them compatible.

[vishal16babu]

Thanks @auspicious3000 , I will give it a try

[vishal16babu]

Hi @auspicious3000 ,
I looked at the spectrogram calculation code and it does not look like a straightforward mel spectrogram calculation. I also tried using librosa.feature.inverse.mel_to_audio(spec, sr=16000, n_fft=1024) to get audio using Griffin-Lim instead of WaveNet and it resulted in a garbage signal as expected.

1. Is there any specific reason why you're not using direct mel spectrograms as input features to the network?
2. How to invert the spectrograms returned by the network using Griffin-Lim or anything other than a Wavenet trained on these custom spectrograms?

P.S: I am not very familiar with common preprocessing techniques to calculate spectrograms. So any references which can help me understand the motivation behind spectrogram calculation code are very much appreciated

[auspicious3000]

1. To make it compatible with the wavenet vocoder.
2. You can train other vocoders as long as the spectograms are consistent.