{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T08:02:40Z","timestamp":1763193760141,"version":"3.45.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11231007","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Sub-Genre Classification For Mainstage Dance Music"],"prefix":"10.1109","author":[{"given":"Hongzhi","family":"Shu","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Baltimore,USA"}]},{"given":"Xinglin","family":"Li","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China"}]},{"given":"Hongyu","family":"Jiang","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,Changsha,China"}]},{"given":"Minghao","family":"Fu","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence,Abu Dhabi,UAE"}]},{"given":"Xinyu","family":"Li","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence,Abu Dhabi,UAE"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"article-title":"FMA: A Dataset for Music Analysis","volume-title":"18th International Society for Music Information Retrieval Conference (ISMIR)","author":"Defferrard","key":"ref2"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1145\/3184558.3192310","article-title":"Learning to Recognize Musical Genre from Audio","volume-title":"The 2018 Web Conference Companion","author":"Defferrard"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.194"},{"article-title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","year":"2023","author":"Chu","key":"ref5"},{"article-title":"Qwen2-Audio Technical Report","year":"2024","author":"Chu","key":"ref6"},{"article-title":"Qwen2.5-Omni Technical Report","year":"2025","author":"Xu","key":"ref7"},{"year":"2025","key":"ref8","article-title":"Kimi-Audio Technical Report"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980316"},{"key":"ref10","first-page":"3","article-title":"Constant-Q transform toolbox for music processing","volume-title":"7th Sound and Music Computing Conference (SMC)","author":"Sch\u00f6rkhuber"},{"article-title":"A Matlab Toolbox for Efficient Perfect Reconstruction Time-Frequency Transforms with Log-Frequency Resolution","volume-title":"Proceedings of the AES International Conference","author":"Sch\u00f6rkhuber","key":"ref11"},{"key":"ref12","first-page":"153","article-title":"A Survey of Music Information Retrieval Systems","volume-title":"Proceedings of the International Conference on Music Information Retrieval","author":"Typke"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1561\/1500000042"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/mmrp.2019.00012"},{"key":"ref15","first-page":"591","article-title":"The Million Song Dataset","volume-title":"Proceedings of the 12th International Society for Music Information Retrieval Conference","author":"Bertin-Mahieux"},{"article-title":"MusicLM: Generating Music From Text","year":"2023","author":"Agostinelli","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2020.1761399"},{"article-title":"Deep Learning Based EDM Subgenre Classification using Mel-Spectrogram and Tempogram Features","year":"2021","author":"Hsu","key":"ref18"},{"article-title":"Cue Point Estimation using Object Detection","year":"2024","author":"Arg\u00fcello","key":"ref19"},{"key":"ref20","first-page":"143","article-title":"Detecting Drops in Electronic Dance Music: Content based approaches to a socially significant music event","volume-title":"Proceedings of the 15th International Society for Music Information Retrieval Conference, ISMIR 2014, Taipei, Taiwan, October 27-31, 2014","author":"Yadati"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.14"},{"article-title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","year":"2023","author":"Liu","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.231"},{"article-title":"Qwen2-Audio Technical Report","year":"2024","author":"Chu","key":"ref24"},{"key":"ref25","first-page":"770","article-title":"Deep Residual Learning for Image Recognition","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He"},{"key":"ref26","first-page":"2261","article-title":"Densely Connected Convolutional Networks","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Huang"},{"key":"ref27","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","volume-title":"CoRR","author":"Simonyan","year":"2014"},{"article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","year":"2021","author":"Dosovitskiy","key":"ref28"},{"article-title":"Robust Speech Recognition via Large-Scale Weak Supervision","year":"2022","author":"Radford","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"86","key":"ref34","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume-title":"Journal of Machine Learning Research","volume":"9","author":"van der Maaten","year":"2008"},{"article-title":"UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction","year":"2020","author":"McInnes","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"article-title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","year":"2023","author":"Li","key":"ref37"},{"article-title":"A Foundation Model for Music Informatics","year":"2023","author":"Won","key":"ref38"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1109\/TASLPRO.2025.3602320","article-title":"MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization","author":"Zhu","year":"2025"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2025,10,12]]},"location":"Tahoe City, CA, USA","end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11231007.pdf?arnumber=11231007","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:57:56Z","timestamp":1763193476000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11231007\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11231007","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}