Papers › Acoustic scene analysis with multi-head attention networks

Acoustic scene analysis with multi-head attention networks

16 Sep 2019arXiv:1909.08961archive 2025-07-28

Weimin Wang, Weiran Wang, Ming Sun, Chao Wang

Acoustic Scene Classification (ASC) is a challenging task, as a single scene may involve multiple events that contain complex sound patterns. For example, a cooking scene may contain several sound sources including silverware clinking, chopping, frying, etc. What complicates ASC more is that classes of different activities could have overlapping sounds patterns (e.g. both cooking and dishwashing could have silverware clinking sound). In this paper, we propose a multi-head attention network to model the complex temporal input structures for ASC. The proposed network takes the audio's time-frequency representation as input, and it leverages standard VGG plus LSTM layers to extract high-level feature representation. Further more, it applies multiple attention heads to summarize various patterns of sound events into fixed dimensional representation, for the purpose of final scene classification. The whole network is trained in an end-to-end fashion with back-propagation. Experimental results confirm that our model discovers meaningful sound patterns through the attention mechanism, without using explicit supervision in the alignment. We evaluated our proposed model using DCASE 2018 Task 5 dataset, and achieved competitive performance on par with previous winner's results.

Paper PDF Code

Code

KrishnaDN/acoustic-scene-analysis-with-multihead-self-attention mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Acoustic Scene Classification General Classification Scene Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Attention Convolution Dense Connections Dropout LSTM Linear Layer Max Pooling Multi-Head Attention ReLU Sigmoid Activation Softmax Tanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections