Audio Classification

This is a competition from AI CUP 2023. We are TEAM_2907.

Proposed Pipeline

Requirements

Software

If you want to run in a virtual environment,

conda create --name audio python=3.10
conda activate audio
pip install -r requirements.txt

Hardware

Type	Name
os	Ubuntu 22.04.1 LTS
cpu	Intel(R) Xeon(R) CPU E5-2690 v3 @ 2.60GHz
gpu	NVIDIA GeForce GTX 1080 Ti

Data Preprocessing

python WavEncoder.py --train_wav <training_audio_directory> \
                     --public_wav <public_audio_directory> \
                     --private_wav <private_audio_directory> \
                     --train_csv <training_csv_directory> \
                     --public_csv <public_csv_directory> \
                     --private_csv <private_csv_directory> \
                     --output_path <output_path>

Reproduce

bash ./run_reproduce.sh

Citation

@misc{
    title  = {multimodal_pathological_voice_classification},
    author = {Chun-Hsien Chen, Shu-Cheng Zheng, Jia-Wei Liao, Yi-Cheng Hung},
    url    = {https://github.com/jwliao1209/Audio-Classification},
    year   = {2023}
}