What question did this study set out to answer?

To develop and evaluate large-scale pretrained audio neural networks (PANNs) that transfer effectively across diverse audio pattern recognition tasks.

January 1, 2020IEEE/ACM Transactions on Audio Speech and Language Processing

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

View Full Paper

Ask AI

Bookmark

To develop and evaluate large-scale pretrained audio neural networks (PANNs) that transfer effectively across diverse audio pattern recognition tasks.
Trained multiple convolutional neural network architectures on the large-scale AudioSet dataset.
Developed Wavegram-Logmel-CNN, an architecture incorporating both raw waveforms and log-mel spectrograms as joint input features.
Evaluated performance, computational complexity, and transferability across six downstream audio pattern recognition tasks.
The top-performing PANN model achieved a state-of-the-art mean average precision of 0.439 on AudioSet tagging, outperforming the previous benchmark of 0.392.
Transferring PANNs to six distinct audio pattern recognition tasks established state-of-the-art performance across several downstream benchmarks.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Experimental evaluation demonstrates state-of-the-art tagging performance across six audio pattern recognition benchmarks, indicating the effectiveness of large-scale pretraining.

Cite This Study

Kong et al. (2020) studied this question.

synapsesocial.com/papers/69d851298c03fbaff8beef49 https://doi.org/10.1109/taslp.2020.3030497

View Full Paper

Ask AI

Bookmark

Implication

Experimental evaluation demonstrates state-of-the-art tagging performance across six audio pattern recognition benchmarks, indicating the effectiveness of large-scale pretraining.

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

Key Points

Discussion

Implication

Cite This Study

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

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider