speechbrain / speechbrain/speechbrain

SpecAugment should not mask in padding

Open
#1,116 4 comments 0 reactions 1 assignee View on GitHub

@mravanelli is already working on this.

Since Nov 17, 2021.

bug
Dominant language
Python
Stars
11.8k
Forks
1.7k
No merged PRs in 30d

Description

When given a batch, the current SpecAugment implementation does not take the different lengths of the samples into account. It can happen that the time-mask is applied to padded areas.
The positions of the time masks should be sampled for each batch element depending on the length of the sample.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.