Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets
Machine Listening Lab, Centre for Digital Music (C4DM), Queen Mary University of London, London E1 4NS, UK
*
Author to whom correspondence should be addressed.
Appl. Sci. 2018, 8(8), 1397; https://doi.org/10.3390/app8081397
Received: 15 June 2018 / Revised: 11 August 2018 / Accepted: 14 August 2018 / Published: 18 August 2018
(This article belongs to the Special Issue Computational Acoustic Scene Analysis)
In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training performance when dealing with this kind of low-resource datasets. We evaluate three data-efficient approaches of training a stacked convolutional and recurrent neural network for the intermediate tasks. Our results show that different methods of training have different advantages and disadvantages.
View Full-Text
Keywords:
deep learning; multi-task learning; audio event detection; audio tagging; weak learning; low-resource data
▼
Show Figures
Graphical abstract
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
-
Externally hosted supplementary file 1
Doi: https://doi.org/10.6084/m9.figshare.6798548.v1
Link: https://figshare.com/articles/Transcriptions_of_NIPS4B_2013_Bird_Challenge_Training_Dataset/6798548
Description: These are the transcription files we produced for the NIPS4B 2013 Bird challenge dataset in order to evaluate our method on a low-resource setting.
MDPI and ACS Style
Morfi, V.; Stowell, D. Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets. Appl. Sci. 2018, 8, 1397. https://doi.org/10.3390/app8081397
AMA Style
Morfi V, Stowell D. Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets. Applied Sciences. 2018; 8(8):1397. https://doi.org/10.3390/app8081397
Chicago/Turabian StyleMorfi, Veronica, and Dan Stowell. 2018. "Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets" Applied Sciences 8, no. 8: 1397. https://doi.org/10.3390/app8081397
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
