New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

How to invert a log-STFT? #136

Open

turian opened this issue Sep 4, 2024 · 0 comments

Contributor

turian commented Sep 4, 2024

I am trying to invert a log STFT from nnAudio but the audio sounds strange and metallic and the NSDRs are much worse on the reconstruction.

This doesn't work:

    stft_layer = STFT(n_fft=n_fft, hop_length=hop_length, freq_scale='log', output_format='Complex', sr=sr)
    stft_output = stft_layer(waveform)

    istft_layer = iSTFT(n_fft=n_fft, hop_length=hop_length, freq_scale='log', sr=sr)
    inverted_waveform = istft_layer(stft_output, onesided=True, length=waveform.shape[-1])  # Set length

But if I remove freq_scale="log" it works just fine. Why?

The text was updated successfully, but these errors were encountered:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment