{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:20:32Z","timestamp":1774419632085,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890872","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Music Tagging with Classifier Group Chains"],"prefix":"10.1109","author":[{"given":"Takuya","family":"Hasumi","sequence":"first","affiliation":[{"name":"LY Corporation,Tokyo,Japan"}]},{"given":"Tatsuya","family":"Komatsu","sequence":"additional","affiliation":[{"name":"LY Corporation,Tokyo,Japan"}]},{"given":"Yusuke","family":"Fujita","sequence":"additional","affiliation":[{"name":"LY Corporation,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Music classification: Beyond supervised learning, towards real-world applications","author":"Won","year":"2021"},{"key":"ref2","first-page":"805","article-title":"Automatic tagging using deep convolutional neural networks","volume-title":"Proceedings of International Society for Music Information Retrieval Conference","author":"Choi"},{"key":"ref3","first-page":"7","article-title":"Sample-level deep convolutional neural networks for music auto-tagging using raw waveforms","volume-title":"Proceedings of Sound and Music Computing Conference","author":"Lee"},{"key":"ref4","first-page":"637","article-title":"End-to-end learning for music audio tagging at scale","volume-title":"Proceedings of International Society for Music Information Retrieval Conference","author":"Pons"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462046"},{"key":"ref6","first-page":"67","article-title":"Zeroshot learning for audio-based music classification and tagging","volume-title":"Proceedings of International Society for Music Information Retrieval Conference","author":"Choi"},{"key":"ref7","article-title":"Toward interpretable music tagging with self-attention","author":"Won","year":"2019"},{"key":"ref8","first-page":"7","article-title":"Evaluation of CNN-based automatic music tagging models","volume-title":"Proceedings of Sound and Music Computing Conference","author":"Won"},{"key":"ref9","first-page":"766","article-title":"Semi-supervised music tagging transformer","volume-title":"Proceedings of International Society for Music Information Retrieval Conference","author":"Won"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746996"},{"key":"ref11","first-page":"256","article-title":"Supervised and unsupervised learning of audio representations for music understanding","volume-title":"Proceedings of 23rd International Society for Music Information Retrieval Conference","author":"McCallum"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094670"},{"key":"ref13","first-page":"220","article-title":"Leveraging hierarchical structures for few-shot musical instrument recognition","volume-title":"Proceedings of International Society for Music Information Retrieval Conference","author":"Garcia"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095162"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326814"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5256-5"},{"key":"ref17","first-page":"279","article-title":"Bayes optimal multilabel classification via probabilistic classifier chains","volume-title":"Proceedings of International Conference on Machine Learning","author":"Cheng"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2418"},{"key":"ref19","article-title":"Neural speaker diarization with speaker-wise chain rule","author":"Fujita","year":"2020"},{"key":"ref20","first-page":"3735","article-title":"Sequence to multi-sequence learning via conditional chain mapping for mixture signals","volume-title":"Proceedings of Neural Information Processing Systems","author":"Shi"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2218"},{"key":"ref22","article-title":"The MTG-Jamendo dataset for automatic music tagging","volume-title":"Machine Learning for Music Discovery Workshop, International Conference on Machine Learning","author":"Bogdanov"},{"key":"ref23","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref26","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proceedings of International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref27","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proceedings of International Conference on Machine Learning","author":"Touvron"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref29","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref31","first-page":"67","article-title":"Music autotagging as captioning","volume-title":"Proceedings of Workshop on NLP for Music and Audio","author":"Cai"},{"key":"ref32","first-page":"409","article-title":"LP-MusicCaps: LLM-based pseudo music captioning","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference","author":"Doh"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890872.pdf?arnumber=10890872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:51Z","timestamp":1774416231000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890872","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}