Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets
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 amou...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-08-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2076-3417/8/8/1397 |
| _version_ | 1818839239111999488 |
|---|---|
| author | Veronica Morfi Dan Stowell |
| author_facet | Veronica Morfi Dan Stowell |
| author_sort | Veronica Morfi |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-19T03:51:07Z |
| format | Article |
| id | doaj.art-f252b1f5cff746c499f6da1be2cb1395 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-19T03:51:07Z |
| publishDate | 2018-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-f252b1f5cff746c499f6da1be2cb13952022-12-21T20:37:00ZengMDPI AGApplied Sciences2076-34172018-08-0188139710.3390/app8081397app8081397Deep Learning for Audio Event Detection and Tagging on Low-Resource DatasetsVeronica Morfi0Dan Stowell1Machine Listening Lab, Centre for Digital Music (C4DM), Queen Mary University of London, London E1 4NS, UKMachine Listening Lab, Centre for Digital Music (C4DM), Queen Mary University of London, London E1 4NS, UKIn 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.http://www.mdpi.com/2076-3417/8/8/1397deep learningmulti-task learningaudio event detectionaudio taggingweak learninglow-resource data |
| spellingShingle | Veronica Morfi Dan Stowell Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets Applied Sciences deep learning multi-task learning audio event detection audio tagging weak learning low-resource data |
| title | Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets |
| title_full | Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets |
| title_fullStr | Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets |
| title_full_unstemmed | Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets |
| title_short | Deep Learning for Audio Event Detection and Tagging on Low-Resource Datasets |
| title_sort | deep learning for audio event detection and tagging on low resource datasets |
| topic | deep learning multi-task learning audio event detection audio tagging weak learning low-resource data |
| url | http://www.mdpi.com/2076-3417/8/8/1397 |
| work_keys_str_mv | AT veronicamorfi deeplearningforaudioeventdetectionandtaggingonlowresourcedatasets AT danstowell deeplearningforaudioeventdetectionandtaggingonlowresourcedatasets |