# Spatio-Temporal Attention Pooling for Audio Scene Classification

arXiv: https://arxiv.org/abs/1904.03543 · HTML: https://mlsanity.com/paper/1904.03543/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2019.

## Built on by (most cited first, 6 of 6)

- [Multi-view Audio and Music Classification](https://mlsanity.com/paper/2103.02420/) (2021)
- [Unlocking the potential of deep learning for marine ecology: overview, applications, and outlook](https://mlsanity.com/paper/2109.14737/) (2021)
- [Attentive max feature map and joint training for acoustic scene classification](https://mlsanity.com/paper/2104.07213/) (2021)
- [Low-complexity deep learning frameworks for acoustic scene classification](https://mlsanity.com/paper/2206.06057/) (2022)
- [Ordinal-Quadruplet: Retrieval of Missing Classes in Ordinal Time Series](https://mlsanity.com/paper/2201.09907/) (2022)
- [Low-complexity deep learning frameworks for acoustic scene classification using teacher-student scheme and multiple spectrograms](https://mlsanity.com/paper/2305.09463/) (2023)

## Abstract (arXiv)

Acoustic scenes are rich and redundant in their content. In this work, we present a spatio-temporal attention pooling layer coupled with a convolutional recurrent neural network to learn from patterns that are discriminative while suppressing those that are irrelevant for acoustic scene classification. The convolutional layers in this network learn invariant features from time-frequency input. The bidirectional recurrent layers are then able to encode the temporal dynamics of the resulting convolutional features. Afterwards, a two-dimensional attention mask is formed via the outer product of the spatial and temporal attention vectors learned from two designated attention layers to weigh and pool the recurrent output into a final feature vector for classification. The network is trained with between-class examples generated from between-class data augmentation. Experiments demonstrate that the proposed method not only outperforms a strong convolutional neural network baseline but also sets new state-of-the-art performance on the LITIS Rouen dataset.