Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets
AbstractIn 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
Externally hosted supplementary file 1
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.
Share & Cite This Article
Morfi, V.; Stowell, D. Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets. Appl. Sci. 2018, 8, 1397.
Morfi V, Stowell D. Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets. Applied Sciences. 2018; 8(8):1397.Chicago/Turabian Style
Morfi, Veronica; Stowell, Dan. 2018. "Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets." Appl. Sci. 8, no. 8: 1397.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.