Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets
Open Access
- 18 August 2018
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 8 (8) , 1397
Abstract
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.Keywords
All Related Versions
Funding Information
- Engineering and Physical Sciences Research Council (EP/L020505/1)
This publication has 23 references indexed in Scilit:
- Adaptive Pooling in Multi-instance Learning for Web Video Annotation2017
- An overview of multi-task learningNational Science Review, 2017
- Speaker diarization using deep neural network embeddings2017
- A joint detection-classification model for audio tagging of weakly labelled data2017
- CNN architectures for large-scale audio classification2017
- Cross-Stitch Networks for Multi-task Learning2016
- Recurrent neural networks for polyphonic sound event detection in real life recordings2016
- Deep learningNature, 2015
- Multitask LearningMachine Learning, 1997
- Solving the multiple instance problem with axis-parallel rectanglesArtificial Intelligence, 1997