[A-8] Signal Processing

2:30 PM - 2:45 PM JST(5:30 AM - 5:45 AM UTC)Candidate for Academic Incentive Award

[A-8-15] Detecting Misophonia Trigger Sounds on Synthetic Soundscapes with Hybrid Approaches Combining a Frozen CNN and a Time-series Model

◎Kurumi Sashida¹, Gouhei Tanaka^1,2 (1. Nagoya Institute of Technology, 2. The University of Tokyo)

Keywords:

Misophonia,Sound Event Detection,Echo State Network,Frozen CNN,Lightweight

Password required to view