Page 58 - 《应用声学》2022年第3期

380 2022 年 5 月

International Conference on Machine Learning, 1993: international conference on Multimedia, 2014: 1041–1044.
41–48. [15] Boddapati V, Petef A, Rasmusson J, et al. Classify-
[7] Hinton G, Vinyals O, Dean J. Distilling the knowledge ing environmental sounds using image recognition net-
in a neural network[J]. Computer Science, 2015, arXiv: works[C]// Procedia Computer Science, 2017: 2048–2056.
1503.02531v1.
[16] Tokozume Y, Harada T. Learning environmental sounds
[8] Søgaard A, Goldberg Y. Deep multi-task learning with low
with end-to-end convolutional neural network[C]// IEEE
level tasks supervised at lower layers[C]//Proceedings of International Conference on Acoustics, Speech and Signal
the 54th Annual Meeting of the Association for Compu- Processing (ICASSP), 2017: 2721–2725.
tational Linguistics, 2016: 231–235.
[17] Piczak K J. Environmental sound classification with con-
[9] Zhao R, Pandit V, Qian K, et al. Deep sequential im-
volutional neural networks[C]//IEEE 25th International
age features on acoustic scene classification[C]// Work-
Workshop on Machine Learning for Signal Processing
shop on Detection and Classification of Acoustic Scenes
(MLSP), 2015: 1–6.
and Events, 2017.
[18] Tokozume Y, Ushiku Y, Harada T. Learning from
[10] Chen H, Liu Z, Liu Z, et al. Integrating the data augmen-
between-class examples for deep sound recognition[C]//
tation scheme with various classifiers for acoustic scene
arXiv Preprint, arXiv: 1711.10282.
modeling[J]. arXiv Preprint, arXiv: 1907.06639.
[11] Ioffe S, Szegedy C. Batch normalization: accelerating deep [19] Zhang Z, Xu S, Cao S, et al. Deep convolutional neu-
network training by reducing internal covariate shift[J]. ral network with mixup for environmental sound clas-
sification[C]//Pattern Recognition and Computer Vision
arXiv Preprint, arXiv: 1502.03167, 2015.
(PRCV), 2018: 356–367.
[12] Nair V, Hinton G E. Rectified linear units improve re-
stricted boltzmann machines[C]//Proceedings of the 27th [20] Agrawal D, Sailor H, Soni M, et al. Novel TEO-based
International Conference on Machine Learning, 2010: Gammatone features for environmental sound classifica-
807–814. tion[C]// in 2017 25th European Signal Processing Con-
[13] Piczak K J. ESC: dataset for environmental sound clas- ference (EUSIPCO). 2017: 1809–1813.
sification[C]//Proceedings of the 23rd Annual ACM Con- [21] Abdoli S, Cardinal P, Koerich A. End-to-end environ-
ference on Multimedia, 2015: 1015–1018. mental sound classification using a 1d convolutional neu-
[14] Salamon J, Jacoby C, Bello J. A dataset and taxonomy for ral network[C]//Expert Systems with Applications, 2019:
urban sound research[C]// Proceedings of the 22nd ACM 252–263.