I. Laboratories: https://fmi-unibuc-ia.github.io/ia/
II. Surgical mask detection Project
In the surgical mask detection task, participants have to discriminate between utterances with and without surgical masks. The system could be useful in the context of the COVID-19 pandemic, by allowing the automatic verification of surgical mask wearing from speech. This is a binary classification task in which an utterance (audio file) must be labeled as without mask (label 0) or with mask (label 1).
The training data is composed of 8000 audio files. The validation set is composed of 1000 audio files. The test is composed of 3000 audio files.
File Descriptions
train.txt - the training metadata file containing the audio file names and the corresponding labels (one example per row) validation.txt - the validation metadata file containing the audio file names and the corresponding labels (one example per row) test.txt - the test metadata file containing the audio file names (one sample per row) sample_submission.txt - a sample submission file in the correct format
Kaggle competition: https://www.kaggle.com/c/ml-fmi-23-2020/overview