Comparing time and frequency domain for audio event recognition using deep learning

L. Hertel, H. Phan, A. Mertins

Abstract

Recognizing acoustic events is an intricate problem for a machine and an emerging field of research. Deep neural networks achieve convincing results and are currently the state-of-the-art approach for many tasks. One advantage is their implicit feature learning, opposite to an explicit feature extraction of the input signal. In this work, we analyzed whether more discriminative features can be learned from either the time-domain or the frequency-domain representation of the audio signal. For this purpose, we trained multiple deep networks with different architectures on the Freiburg-106 and ESC-10 datasets. Our results show that feature learning from the frequency domain is superior to the time domain. Moreover, additionally using convolution and pooling layers, to explore local structures of the audio signal, significantly improves the recognition performance and achieves state-of-the-art results.
OriginalspracheEnglisch
Titel2016 International Joint Conference on Neural Networks (IJCNN)
Seitenumfang5
Herausgeber (Verlag)IEEE
Erscheinungsdatum03.11.2016
Seiten3407-3411
ISBN (Print)978-1-5090-0621-2
ISBN (elektronisch)978-1-5090-0620-5
DOIs
PublikationsstatusVeröffentlicht - 03.11.2016
Veranstaltung2016 International Joint Conference on Neural Networks (IJCNN) - Vancouver, Kanada
Dauer: 24.07.201629.07.2016

Fingerprint

Untersuchen Sie die Forschungsthemen von „Comparing time and frequency domain for audio event recognition using deep learning“. Zusammen bilden sie einen einzigartigen Fingerprint.

Zitieren