Skip to content

fix bug in reverberate with rescale_amp #2871

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

Merged
pplantinga merged 4 commits into from
May 21, 2025
Merged

fix bug in reverberate with rescale_amp #2871

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
26f889d
fix bug in reverberate with rescale_amp
ofiryaish Mar 31, 2025
27967f2
Merge branch 'develop' into fix-rescale-amplitude
ofiryaish Apr 2, 2025
e261c48
Merge branch 'develop' into fix-rescale-amplitude
TParcollet Apr 7, 2025
bfdaa78
Merge branch 'develop' into fix-rescale-amplitude
ofiryaish Apr 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 15 additions & 12 deletions speechbrain/processing/signal_processing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -330,8 +330,8 @@ def reverberate(waveforms, rir_waveform, rescale_amp="avg"):
Shape should be `[batch, time]` or `[batch, time, channels]`.
rir_waveform : tensor
RIR tensor, shape should be [time, channels].
rescale_amp : str
Whether reverberated signal is rescaled (None) and with respect either
rescale_amp : str or None
Whether reverberated signal is rescaled (None to avoid) and with respect either
to original signal "peak" amplitude or "avg" average amplitude.
Choose between [None, "avg", "peak"].

Expand All @@ -356,10 +356,11 @@ def reverberate(waveforms, rir_waveform, rescale_amp="avg"):
elif len(rir_waveform.shape) == 2:
rir_waveform = rir_waveform.unsqueeze(-1)

# Compute the average amplitude of the clean
orig_amplitude = compute_amplitude(
waveforms, waveforms.size(1), rescale_amp
)
if rescale_amp is not None:
# Compute the average amplitude of the clean
orig_amplitude = compute_amplitude(
waveforms, waveforms.size(1), rescale_amp
)

# Compute index of the direct signal, so we can preserve alignment
value_max, direct_index = rir_waveform.abs().max(axis=1, keepdim=True)
Expand All @@ -376,10 +377,11 @@ def reverberate(waveforms, rir_waveform, rescale_amp="avg"):
rotation_index=direct_index,
)

# Rescale to the peak amplitude of the clean waveform
waveforms = rescale(
waveforms, waveforms.size(1), orig_amplitude, rescale_amp
)
if rescale_amp is not None:
# Rescale to the peak amplitude of the clean waveform
waveforms = rescale(
waveforms, waveforms.size(1), orig_amplitude, rescale_amp
)

if len(orig_shape) == 1:
waveforms = waveforms.squeeze(0).squeeze(-1)
Expand Down Expand Up @@ -457,7 +459,7 @@ def _sinc(x):
return torch.sin(x) / x

# The zero is at the middle index
return torch.cat([_sinc(x[:pad]), torch.ones(1), _sinc(x[pad + 1 :])])
return torch.cat([_sinc(x[:pad]), torch.ones(1), _sinc(x[pad + 1:])])

# Compute a low-pass filter with cutoff frequency notch_freq.
hlpf = sinc(3 * (notch_freq - notch_width) * inputs)
Expand Down Expand Up @@ -494,7 +496,8 @@ def overlap_and_add(signal, frame_step):
-------
A Tensor with shape [..., output_size] containing the overlap-added frames of signal's inner-most two dimensions.
output_size = (frames - 1) * frame_step + frame_length
Based on https://github.com/tensorflow/tensorflow/blob/r1.12/tensorflow/contrib/signal/python/ops/reconstruction_ops.py
Based on
https://github.com/tensorflow/tensorflow/blob/r1.12/tensorflow/contrib/signal/python/ops/reconstruction_ops.py

Example
-------
Expand Down