합성곱 신경망 기반 환경잡음에 강인한 교통 소음 분류 모델 = Convolutional neural network based traffic sound classification robust to environmental noise

다국어 초록 (Multilingual Abstract)

As urban population increases, research on urban environmental noise is getting more attention. In this study, we classify the abnormal noise occurring in traffic situation by using a deep learning algorithm which shows high performance in recent environmental noise classification studies. Specifically, we classify the four classes of tire skidding sounds, car crash sounds, car horn sounds, and normal sounds using convolutional neural networks. In addition, we add three environmental noises, including rain, wind and crowd noises, to our training data so that the classification model is more robust in real traffic situation with environmental noises. Experimental results show that the proposed traffic sound classification model achieves better performance than the existing algorithms, particularly under harsh conditions with environmental noises.

참고문헌 (Reference)

1 B. McFee, "librosa: Audio and music signal analysis in python" 18-25, 2015

2 "http://www.freesound.org"

3 M. Abadi, "Tensorflow: a system for large-scale machine learning" 16 : 265-283, 2016

4 R. Banerjee, "Participatory sensing based traffic condition monitoring using horn detection" 567-569, 2013

5 K. J. Piczak, "Environmental sound classification with convolutional neural networks" 1-6, 2015

6 J. Salamon, "Deep convolutional neural networks and data augmentation for environmental sound classification" 24 : 279-283, 2017

7 M. Cristani, "Audio-visual event recognition in surveillance video sequences" 9 : 257-267, 2007

8 P. Foggia, "Audio surveillance of roads: A system for detecting anomalous sounds" 17 : 279-288, 2016

9 J. Salamon, "A dataset and taxonomy for urban sound research" 1041-1044, 2014