Conference proceeding
Acoustic Scene Analysis with Multi-head Attention Networks
INTERSPEECH 2020, Vol.2020-, pp.1191-1195
Interspeech
01/01/2020
DOI: 10.21437/Interspeech.2020-1342
Abstract
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 backpropagation. 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.
Details
- Title: Subtitle
- Acoustic Scene Analysis with Multi-head Attention Networks
- Creators
- Weimin Wang - Amazon Alexa, Seattle, WA 98109 USAWeiran Wang - SalesforceMing Sun - Amazon Alexa, Seattle, WA 98109 USAChao Wang - Amazon Alexa, Seattle, WA 98109 USA
- Resource Type
- Conference proceeding
- Publication Details
- INTERSPEECH 2020, Vol.2020-, pp.1191-1195
- Publisher
- Isca-Int Speech Communication Assoc
- Series
- Interspeech
- DOI
- 10.21437/Interspeech.2020-1342
- ISSN
- 2308-457X
- eISSN
- 1990-9772
- Number of pages
- 5
- Language
- English
- Date published
- 01/01/2020
- Academic Unit
- Computer Science
- Record Identifier
- 9984696714502771
Metrics
2 Record Views