DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Nam, Juhan | - |
dc.contributor.advisor | 남주한 | - |
dc.contributor.author | Choi, Jeong | - |
dc.date.accessioned | 2021-05-12T19:36:47Z | - |
dc.date.available | 2021-05-12T19:36:47Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=910804&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/284012 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 문화기술대학원, 2020.2,[iii, 24 :] | - |
dc.description.abstract | Audio-based music classification and tagging is typically based on categorical supervised learning with a fixed set of labels. This intrinsically cannot handle unseen labels such as newly added music genres or semantic words that users arbitrarily choose for music retrieval. Zero-shot learning can address this problem by leveraging an additional semantic space of labels where side information about the labels is used to unveil the relationship between each other. In this work, we investigate the zero-shot learning in the music domain and organize two different setups of side information. One is using human-labeled attribute information based on Free Music Archive and OpenMIC-2018 datasets. The other is using general word semantic information based on Million Song Dataset and Last.fm tag annotations. Considering a music track is usually multi-labeled in music classification and tagging datasets, we also propose a data split scheme and associated evaluation settings for the multi-label zero-shot learning. We report experimental results to show that the zero-shot learning model is effective in both annotation and retrieval tasks for music. We further verify the generalization ability of zero-shot learning model by conducting knowledge transfer to different music corpora. We finally discuss the new possibilities of zero-shot learning in the music domain. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Audio-based music classification▼aZero-shot learning▼aKnowledge transfer | - |
dc.subject | 오디오기반음악분류▼a제로샷러닝 | - |
dc.title | Zero-shot learning for audio-based music classification and tagging | - |
dc.title.alternative | 오디오 기반 음악 자동 태깅 및 분류를 위한 제로샷 학습 모델에 대한 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :문화기술대학원, | - |
dc.contributor.alternativeauthor | 최정 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.