em474re/CovidSpeechChallenge_2021
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity
7 Commits 1 Branch 0 Tags 1.5 GiB
Python 99.1%
Shell 0.9%
6b3fbce6d1
Go to file
em474re 6b3fbce6d1 update results
2021-09-01 15:40:59 +02:00
vggish add VGGSH tool 2021-08-19 09:06:30 +02:00
extract_handcrafted_features.py svm model for handcrafted and vggsh features 2021-08-19 10:39:47 +02:00
extract_vgg_features.py svm model for handcrafted and vggsh features 2021-08-19 10:39:47 +02:00
presentation_results.pptx update results 2021-09-01 15:40:59 +02:00
README.md svm model for handcrafted and vggsh features 2021-08-19 10:39:47 +02:00
run_experiments.sh run_experiments.sh 2021-08-19 10:43:28 +02:00
svm.py svm model for handcrafted and vggsh features 2021-08-19 10:39:47 +02:00
transformer.py transformer model 2021-08-24 10:44:14 +02:00

README.md

covid-19 speech diagnosis

This repo contains the code created by Elien Martens during IAESTE internship summer 2021, Technical University Kosice (Slowakia).

Dataset

The COVID-19 datasets can be obtained through The University of Cambridge. (see also compare.openaudio.eu, Interspeech Computational Paralinguistics Challenges 2021)

How it works

  • clone repo
  • add data (see Dataset section above), so that the structuring is the following: CovidSpeechChallenge -> raw_files -> train -> test -> devel -> labels -> vgg_features -> hand_features -> vggish ...
  • run .\run_experiments.sh