PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition

Short summary

Pretrained Audio Neural Networks (PANNs) trained on the large-scale AudioSet dataset achieve state-of-the-art performance on audio pattern recognition tasks, with the best system reaching a 0.439 mAP on AudioSet tagging, surpassing the previous best of 0.392.

AI-generated from the title and abstract; the full text is not read.