3
$\begingroup$

I have few thousand audio signals to label into 2 different classes and save them to numpy array for further training of models. MATLAB recently released Signal Labeler for their Signal Analyzer, that could help to label time series, but for certain reasons, I can't use it.

Is there any specific tool for analysis and labeling of time series for Python? It is not necessary to save data and labels into numpy arrays, .csv format or anything similar is suitable as well.

Will appreciate any help!

$\endgroup$
2
$\begingroup$

Audacity is a free and open source audio editing software, available for all common desktop operating systems. It can be used to annotate audio, by using Label Tracks. You can have a label at a certain position, or covering a selection of time.

Annotating

  1. Open or import your audio into Audacity
  2. Select the audio track you want to annotate.
  3. Click Track -> Edit Labels to add a new Label track
  4. Select where in the track you want to annotate
  5. Insert new label using keyboard shortcut Ctrl + B

Repeat until done with the track.

Audacity with a label track

Export annotations

Export the labels using File -> Export -> Export Labels

Loading annotations

To load the labels into Python, you can use this snippet of code:

import pandas

path = 'PATH/TO/FILE'
labels = pandas.read_csv(path, sep='\t', header=None,
                        names=['start', 'end', 'annotation'],
                        dtype=dict(start=float,end=float,annotation=str))
$\endgroup$
  • $\begingroup$ Thanks a lot, I'll definitely try this! $\endgroup$ – Alexey Abramov Jul 25 at 12:42
0
$\begingroup$

Try this one: https://labelstud.io, it is a free opensource tool via web browser with a good documentation and a lot of examples. Easy to start.

Or if you need a teamwork you can use the labeling platform: https://heartex.ai.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.