https://scholars.lib.ntu.edu.tw/handle/123456789/580831
標題: | Tag Propagation and Cost-Sensitive Learning for Music Auto-Tagging | 作者: | Lin Y.-H HOMER H. CHEN |
關鍵字: | Multimedia systems; Signal processing; Cost-sensitive; Cost-sensitive learning; False negatives; Labeled training data; Learning methods; Loss functions; Similarity measurements; Tag propagation; Learning systems | 公開日期: | 2021 | 卷: | 23 | 起(迄)頁: | 1605-1616 | 來源出版物: | IEEE Transactions on Multimedia | 摘要: | The performance of music auto-tagging depends on the quality of training data. In practice, the links between songs and tags in the manually labeled training data can be incorrect (false positive) or missing (false negative). In this paper, we propose a cost-sensitive tag propagation learning method to improve auto-tagging. Specifically, we exploit music context to determine similar songs and propagate tags between them. Both propagated tags and original tags are used to optimize the auto-tagging models, and cost-sensitivity is incorporated into the loss function to enhance the robustness by adjusting the weight of relevant (positive) links with respect to irrelevant (negative) links. The proposed method is tested on three auto-tagging models: 2D-CNN, CRNN, and SampleCNN. The Million Song Dataset is used for training, and four music contexts, artist, playlist, tag, and listener, are used for song similarity measurement. The experimental results show 1) The proposed method can successfully improve the performance of the three auto-tagging models, 2) The cost-sensitive loss function helps reduce the impact of missing tags, and 3) The artist music context is more powerful for tag propagation than the other three music contexts. ? 1999-2012 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85107148368&doi=10.1109%2fTMM.2020.3001521&partnerID=40&md5=146a6faf69181c5637d50eb6e72ef2f9 https://scholars.lib.ntu.edu.tw/handle/123456789/580831 |
ISSN: | 15209210 | DOI: | 10.1109/TMM.2020.3001521 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。