Multi-stream Network With Temporal Attention For Environmental Sound Classification
| Autor: | Katrin Kirchhoff, Xinyu Li, Venkata Subrahmanyam Chandra Sekhar Chebiyyam |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Sound (cs.SD) Computer science media_common.quotation_subject 02 engineering and technology Convolutional neural network Computer Science - Sound Raw audio format Audio and Speech Processing (eess.AS) FOS: Electrical engineering electronic engineering information engineering 0202 electrical engineering electronic engineering information engineering Preprocessor Generalizability theory Function (engineering) media_common Network architecture Audio signal business.industry 020206 networking & telecommunications Pattern recognition Multimedia (cs.MM) 020201 artificial intelligence & image processing Artificial intelligence business Energy (signal processing) Computer Science - Multimedia Electrical Engineering and Systems Science - Audio and Speech Processing |
| Zdroj: | INTERSPEECH |
| Popis: | Environmental sound classification systems often do not perform robustly across different sound classification tasks and audio signals of varying temporal structures. We introduce a multi-stream convolutional neural network with temporal attention that addresses these problems. The network relies on three input streams consisting of raw audio and spectral features and utilizes a temporal attention function computed from energy changes over time. Training and classification utilizes decision fusion and data augmentation techniques that incorporate uncertainty. We evaluate this network on three commonly used data sets for environmental sound and audio scene classification and achieve new state-of-the-art performance without any changes in network architecture or front-end preprocessing, thus demonstrating better generalizability. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|