BROWSE
Detail
Conference Paper
Metric Optimization for Sound Event Localization and Detection
Cited 0 time in 
Share 
Share
- Authors
- Sooyoung Park, Youngho Jeong, Taejin Lee
- Issue Date
- 2020-11
- Citation
- International Conference on Consumer Electronics (ICCE) 2020 : Asia, pp.422-425
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- Due to DNN-based approach, sound event localization and detection is now possible with a simple microphone array. However, this DNN-based sound event localization and detection has problem with dataset imbalance, pooling size decision, and periodicity of angles. In this paper, we propose three methods: soft f-loss with temporal masking, periodic loss, and PoolNet-based architecture to handle three issues. We evaluate our approach on TAU-NIGENS Spatial Sound Events 2020 dataset. The experimental results show our approach shows performance improvement in sound event localization and detection metrics compared to the baseline system.
- KSP Keywords
- Based Approach, Baseline system, Metric optimization, Microphone arrays, Spatial Sound, Temporal masking, event localization, performance improvement, sound events