GIZ NLP Agricultural Keyword Spotter
Classify audio utterances in Luganda and English from Uganda
Prize
$7 000 USD
Time
Ended over 2 years ago
Participants
253 active · 729 enrolled
Helping
Uganda
Advanced
Classification
Automatic Speech Recognition
Natural Language Processing
Agriculture
Text extraction from audio files
Help · 23 Nov 2020, 15:43 · edited 7 minutes later · 4

@zindi

Is it okay to extract words from audio files and then map them to form pseudo labels?

For example; if the extracted word is "so", it is mapped to "sow" as a pseudo label to be used in training

Discussion 4 answers

Yes you may.

With image classification, models pre-trained on imagenet are somewhat of a standard, and often built into popular libraries. For audio there isn't an exact equivalent.

Obviously, we don't want a situation where someone wins because of access to something the other participants didn't have. So in general sourcing, an extra dataset (even a public one) and using that to get an edge would be a potential issue. But if you have a dataset (or even better a pretrained model) in mind that you think would help all entrants, and it's public+free, let us know and we can see about adding it as an allowed source.

24 Nov 2020, 08:36
Upvotes 0

There are free+public speech to text models available in this python library

So can we use the above mentioned library?

It works for some audio files

25 Nov 2020, 03:30
Upvotes 0