Skip to content
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

Reduce word counts for ESPnet-SE++ Joss paper #4844

Merged
merged 11 commits into from Jan 4, 2023
Merged

Reduce word counts for ESPnet-SE++ Joss paper #4844

merged 11 commits into from Jan 4, 2023

Conversation

neillu23
Copy link
Contributor

No description provided.

@codecov
Copy link

codecov bot commented Dec 29, 2022 •
edited

Codecov Report

Merging #4844 (4faf6d8) into master (b12e08c) will increase coverage by 0.05%.
The diff coverage is n/a.

@@            Coverage Diff             @@
##           master    #4844      +/-   ##
==========================================
+ Coverage   80.63%   80.68%   +0.05%     
==========================================
  Files         536      543       +7     
  Lines       47523    48233     +710     
==========================================
+ Hits        38319    38916     +597     
- Misses       9204     9317     +113
Flag Coverage Δ
test_integration_espnet1 66.39% <ø> (ø)
test_integration_espnet2 49.33% <ø> (+0.76%) ⬆️
test_python 69.25% <ø> (+0.08%) ⬆️
test_utils 23.34% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
espnet2/enh/layers/tcn.py 95.47% <0.00%> (-0.43%) ⬇️
espnet2/bin/asr_inference_k2.py 92.69% <0.00%> (-0.39%) ⬇️
espnet2/train/preprocessor.py 27.18% <0.00%> (-0.35%) ⬇️
espnet2/enh/extractor/abs_extractor.py 100.00% <0.00%> (ø)
espnet2/enh/extractor/td_speakerbeam_extractor.py 100.00% <0.00%> (ø)
espnet2/bin/enh_tse_inference.py 91.73% <0.00%> (ø)
espnet2/bin/enh_tse_train.py 100.00% <0.00%> (ø)
espnet2/tasks/enh_tse.py 97.84% <0.00%> (ø)
espnet2/enh/espnet_model_tse.py 80.64% <0.00%> (ø)
espnet2/enh/layers/adapt_layers.py 92.98% <0.00%> (ø)

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more

@sw005320
Copy link
Contributor

The overall design looks good to me.
@Emrys365, can you do the final check?
Then, we can merge this PR.

@neillu23 neillu23 mentioned this pull request Dec 30, 2022
Closed
Emrys365
Emrys365 approved these changes Jan 1, 2023
View reviewed changes
Copy link
Collaborator

@Emrys365 Emrys365 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks a lot @neillu23! I just have a few minor comments. We can merge the PR after they are resolved.

doc/paper/espnet-se++/paper.md Outdated
Comment on lines 198 to 200
The `forward` function of the class follows the general design in ESPnet2:

def forward(self, speech_mix, speech_ref, ...)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Since the description about Trainer is removed, it might be better to add a hyperlink to the definition of Trainer below:

which processes speech and only returns losses for `Trainer` to update the model.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

updated with this hyperlink:
https://github.com/espnet/espnet/blob/master/espnet2/train/trainer.py#L87-L108

doc/paper/espnet-se++/paper.md Outdated
@@ -643,56 +227,9 @@ Calling `SeparateSpeech` and `Speech2Text` with unprocessed audios returns the s

#### SSE
![](https://i.imgur.com/skZ8uDP.png)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you highlight the python code snippet before creating the screenshot? I think it will make the code more readable.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

new screenshot:
截圖 2023-01-02 下午2 00 15

doc/paper/espnet-se++/paper.md Outdated
<!-- This API allows the processing of both short audio samples and long audio samples. For long audio samples, you can set the value of arguments `segment_size`, `hop_size` to perform segment-wise SSE on the input speech. -->
<!-- (optionally `normalize_segment_scale` and `show_progressbar`) -->
<!-- Note that the segment-wise processing is disabled by default. -->

#### Joint-Task
![](https://i.imgur.com/hrj0hJq.png)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ditto

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

new screenshot
截圖 2023-01-02 下午2 00 31

@neillu23
Copy link
Contributor Author

neillu23 commented Jan 2, 2023

Thanks to @Emrys365 and @sw005320 for reviewing! I have updated the PR with these comments

@sw005320 sw005320 merged commit 7669cce into espnet:master Jan 4, 2023
@sw005320
Copy link
Contributor

sw005320 commented Jan 4, 2023

Thanks, @neillu23!

@sw005320 sw005320 added this to the v.202301 milestone Jan 4, 2023
@sw005320 sw005320 added the SE Speech enhancement label Jan 4, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@Emrys365 Emrys365 Emrys365 approved these changes

Assignees
No one assigned
Labels
Documentation SE Speech enhancement
Projects
None yet
Milestone
v.202301
Development

Successfully merging this pull request may close these issues.

None yet
3 participants
@neillu23 @sw005320 @Emrys365