/Sound-Generalization-Demo

Sound generalization demo. This is the demo of our making sense of sound project.

Primary LanguagePython

Sound-Generalization-Demo

Sound generalization demo. This is the demo from our making sense of sound project.

Download models

This is a demo based on our making sense of sound project. Please download the trained model from https://zenodo.org/record/3576602, and save the model in models folder.

Please also check our AudioSet work on https://github.com/qiuqiangkong/audioset_tagging_cnn, where the model of this demo is trained.

Run

Simply run

python MSoS_demo_generalisation.py

Citation

If you use our codes in any format, please consider citing the following paper:

[1] Qiuqiang Kong, Yin Cao, Turab Iqbal, Yuxuan Wang, Wenwu Wang, Mark D. Plumbley. "PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition." arXiv preprint arXiv:1912.10211 (2019).

Authors

Yin Cao, Christian Kroos, Qiuqiang Kong, Turab Iqbal, Wenwu Wang, Mark Plumbley