Add mvdr_weights_rtf to torchaudio.functional #2229
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
mthrok
reviewed
Feb 16, 2022
nateanl
force-pushed
the
refactor_mvdr_2
branch
from
9fa3b44 to
6500986
Compare
hwangjeff
reviewed
Feb 17, 2022
nateanl
changed the title
nateanl
force-pushed
the
refactor_mvdr_2
branch
from
cc53427 to
e47e54c
Compare
mthrok
approved these changes
Feb 25, 2022
| @@ -582,6 +583,45 @@ def test_rnnt_loss_costs_and_gradients_random_data_with_numpy_fp32(self): | |||
| ref_costs, ref_gradients = rnnt_utils.compute_with_numpy_transducer(data=data) | |||
| self._test_costs_and_gradients(data=data, ref_costs=ref_costs, ref_gradients=ref_gradients) | |||
|
|
|||
| def test_mvdr_weights_rtf(self): | |||
mthrok
approved these changes
Feb 25, 2022
torchaudio/functional/functional.py
Outdated
| reference_channel = reference_channel.to(psd_n.dtype) | ||
| scale = torch.einsum("...c,...c->...", [rtf.conj(), reference_channel[..., None, :]]) | ||
| else: | ||
| raise TypeError(f"Unsupported dtype for reference_channel. Found: {type(reference_channel)}.") |
There was a problem hiding this comment.
Similar to https://github.com/pytorch/audio/pull/2231/files#r814462176, please write what is expected.
|
@nateanl has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
Summary: This PR adds ``mvdr_weights_rtf`` method to ``torchaudio.functional``. It computes the MVDR weight matrix based on the solution that applies relative transfer function (RTF). See [the paper](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.725.673&rep=rep1&type=pdf) for the reference. The input arguments are the complex-valued RTF Tensor of the target speech, power spectral density (PSD) matrix of noise, int or one-hot Tensor to indicate the reference channel, respectively. Pull Request resolved: pytorch#2229 Reviewed By: mthrok Differential Revision: D34474119 Pulled By: nateanl fbshipit-source-id: ca20eca4d071ebb99f0b6827613338796f3ec2a2
nateanl
force-pushed
the
refactor_mvdr_2
branch
from
14937a8 to
dc19b0d
Compare
|
This pull request was exported from Phabricator. Differential Revision: D34474119 |
11 tasks
xiaohui-zhang
pushed a commit
to xiaohui-zhang/audio
that referenced
this pull request
May 4, 2022
Summary: This PR adds ``mvdr_weights_rtf`` method to ``torchaudio.functional``. It computes the MVDR weight matrix based on the solution that applies relative transfer function (RTF). See [the paper](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.725.673&rep=rep1&type=pdf) for the reference. The input arguments are the complex-valued RTF Tensor of the target speech, power spectral density (PSD) matrix of noise, int or one-hot Tensor to indicate the reference channel, respectively. Pull Request resolved: pytorch#2229 Reviewed By: mthrok Differential Revision: D34474119 Pulled By: nateanl fbshipit-source-id: 2d6f62cd0858f29ed6e4e03c23dcc11c816204e2
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds
mvdr_weights_rtfmethod totorchaudio.functional.It computes the MVDR weight matrix based on the solution that applies relative transfer function (RTF). See the paper for the reference.
The input arguments are the complex-valued RTF Tensor of the target speech, power spectral density (PSD) matrix of noise, int or one-hot Tensor to indicate the reference channel, respectively.