L. Vrysis, I. Thoidis, C. Dimoulas, and G. Papanikolaou, “Experimenting with 1D CNN Architectures for Generic Audio Classification,” in Proc. AES Convention 148, May 2020, pp. 10329:1-8. [Online]. Available: https://aes.org/publications/elibrary-page/?id=20746
Vrysis L, Thoidis I, Dimoulas C, Papanikolaou G. Experimenting with 1D CNN Architectures for Generic Audio Classification. In: AES Convention 148. Audio Engineering Society; 2020.pp. 10329:1-8. Available from: https://aes.org/publications/elibrary-page/?id=20746
@inproceedings{Vrysis2020_20746,
author = {Vrysis, Lazaros and Thoidis, Iordanis and Dimoulas, Charalampos and Papanikolaou, George},
title = {{Experimenting with 1D CNN Architectures for Generic Audio Classification}},
booktitle = {AES Convention 148},
pages = {10329:1-8},
url = {https://aes.org/publications/elibrary-page/?id=20746},
year = {2020},
month = may,
publisher = {Audio Engineering Society}
}
TY - CPAPER
TI - Experimenting with 1D CNN Architectures for Generic Audio Classification
AU - Vrysis, Lazaros
AU - Thoidis, Iordanis
AU - Dimoulas, Charalampos
AU - Papanikolaou, George
T2 - AES Convention 148
SP - 1
EP - 8
M1 - Paper 10329
PY - 2020
DA - 2020/05/06
UR - https://aes.org/publications/elibrary-page/?id=20746
PB - Audio Engineering Society
LA - en
AB - During the recent years, convolutional neural networks have been the standard on audio semantics, surpassing traditional classification approaches which employed hand-crafted feature engineering as front-end and various classifiers as back-end. Early studies were based on prominent 2D convolutional topologies for image recognition, adapting them to audio classification tasks. After the surge of deep learning in the past decade, real end-to-end audio learning, employing algorithms that directly process waveforms are to become the standard. This paper attempts a comparison between deep neural setups on typical audio classification tasks, focusing on optimizing 1D convolutional neural networks that can be deployed on various audio in-formation retrieval tasks, such as general audio detection and classification, environmental sound or speech emotion recognition.
ER -