You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Should the RIR be resampled to params['fs'], as the audio has been? Or is this handled elsewhere?
This may not have been an issue with the old 16 kHz RIR's, as they incidentally matched the target sample rate. But I noticed the new data now has 48 kHz RIRs.
The text was updated successfully, but these errors were encountered:
I noticed that
fs_rir
does not seem to be used after it's read from the RIR file.https://github.com/microsoft/DNS-Challenge/blob/master/noisyspeech_synthesizer_singleprocess.py#L178
Should the RIR be resampled to
params['fs']
, as the audio has been? Or is this handled elsewhere?This may not have been an issue with the old 16 kHz RIR's, as they incidentally matched the target sample rate. But I noticed the new data now has 48 kHz RIRs.
The text was updated successfully, but these errors were encountered: