At the Speed of Sound: Efficient Audio Scene Classification
| Autor: | Latifur Khan, Cristian Lumezanu, Haifeng Chen, Yuncong Chen, Dongjin Song, Mizoguchi Takehiko, Bo Dong |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
business.industry media_common.quotation_subject ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020206 networking & telecommunications 02 engineering and technology Recurrent neural network Speed of sound 0202 electrical engineering electronic engineering information engineering Robot 020201 artificial intelligence & image processing Relevance (information retrieval) Active listening Computer vision Artificial intelligence Architecture Function (engineering) business media_common |
| Zdroj: | ICMR |
| DOI: | 10.1145/3372278.3390730 |
| Popis: | Efficient audio scene classification is essential for smart sensing platforms such as robots, medical monitoring, surveillance, or autonomous vehicles. We propose a retrieval-based scene classification architecture that combines recurrent neural networks and attention to compute embeddings for short audio segments. We train our framework using a custom audio loss function that captures both the relevance of audio segments within a scene and that of sound events within a segment. Using experiments on real audio scenes, we show that we can discriminate audio scenes with high accuracy after listening in for less than a second. This preserves 93% of the detection accuracy obtained after hearing the entire scene. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|