ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Weakly Labeled Semi-supervised Sound Event Detection using CRNN with Inception Module
Cited - time in scopus Share share facebook twitter linkedin kakaostory
Authors
Wootaek Lim, Sangwon Suh, Youngho Jeong
Issue Date
2018-11
Citation
Detection and Classification of Acoustic Scenes and Events (DCASE) 2018: Workshop, pp.74-77
Language
English
Type
Conference Paper
Abstract
In this paper, we present a method for large-scale detection of sound events using small weakly labeled data proposed in the Detection and Classification of Acoustic Scenes and Events (DCASE) 2018 challenge Task 4. To perform this task, we adopted the convolutional neural network (CNN) and gated recurrent unit (GRU) based bidirectional recurrent neural network (RNN) as our proposed system. In addition, we proposed the Inception module for handling various receptive fields at once in each CNN layer. We also applied the data augmentation method to solve the labeled data shortage problem and applied the event activity detection method for strong label learning. By applying the proposed method to a weakly labeled semi-supervised sound event detection, it was verified that the proposed system provides better performance compared to the DCASE 2018 baseline system.
KSP Keywords
Activity Detection, Augmentation method, Baseline system, Bidirectional Recurrent Neural Network, Convolution neural network(CNN), Data Augmentation, Data shortage, Detection Method, Gated recurrent unit, Receptive field, Recurrent Neural Network(RNN)