Sound Event Detection Based on Beamformed Convolutional Neural Network Using Multi-Microphones

Kim, Jaehun; Noh, Kyoungin; Kim, Jaeha; Chang, Joon Hyuk

doi:10.1109/ICNIDC.2018.8525597

상세 보기

Sound Event Detection Based on Beamformed Convolutional Neural Network Using Multi-Microphones

Kim, Jaehun;
Noh, Kyoungin;
Kim, Jaeha;
Chang, Joon Hyuk

Citations

SCOPUS

1

초록

This paper presents a real environment sound event detection method based on pre-processing technology. Our goal is to improve the performance of the sound event detection using a pre-processing module called parameterized multi-channel non-causal Wiener filter (PMWF). First, we convert the existing 1 channel data to 2 channels through the Room impulse response generator (RIR) module. The reason for 2-channel conversion is that PMWF requires multiple channels for beamforming. Noise cancellation is performed through PMWF and the results are derived through the proposed convolutional neural network model. As a result, we found that this method has a good effect on real-time sound event detection, and we found that peak normalization and median filter also have a good effect.

키워드

Convolutional neural network; Deep neural network; Median filter; Parametric multi-channel Wiener filter; Convolution; Deep neural networks; Digital integrated circuits; Impulse response; Neural networks; Causal Wiener filter; Convolutional neural network; Multichannel Wiener filter; Noise cancellation; Pre-processing technology; Real time sound events; Room impulse response; Sound event detection; Median filters

제목: Sound Event Detection Based on Beamformed Convolutional Neural Network Using Multi-Microphones

저자: Kim, Jaehun; Noh, Kyoungin; Kim, Jaeha; Chang, Joon Hyuk

DOI: 10.1109/ICNIDC.2018.8525597

발행일: 2018-11

유형: Conference Paper

저널명: Proceedings of 2018 6th IEEE International Conference on Network Infrastructure and Digital Content, IC-NIDC 2018

페이지: 170 ~ 173