[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84164-en":3,"doc-seo-84164-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},84164,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","MADB: A Large-Scale Music Aesthetics Dataset with Professional and Multi-Dimensional Annotations","Music aesthetic assessment is a difficult, underexplored task that demands models to learn fine-grained, multi-dimensional human perceptual judgments. Progress has been constrained by the lack of large-scale datasets that include structured aesthetic annotations. MADB introduces a benchmark dataset with 9,999 music tracks annotated by 30 trained annotators, each track rated by about 10 annotators across 10 perceptual dimensions plus an overall score, supported by textual comments for multimodal analysis.","arXiv :2607 .06929v 1 [ cs . SD] 8 Jul 2026  \nMADB: A Large-Scale Music Aesthetics Dataset with Professional and Multi-Dimensional Annotations  \nSirui Zhang 1 ,2 , Tianle Wang 1 ,2 , Xinyi Tong 1 ,2 , Peiyang Yu 1 ,2 , Jishang Chen 1 ,2 ,  \nLiangke Zhao 1 ,2 , Haoxin Zhang 1 ,2 , Duo Xu2 ,3 ,∗ , Xin Jin2 ,4 ,∗ , Feng Yu 1 ,∗ , Songchun Zhu2 ,5 ,∗  \n1 Central Conservatory of Music, China  \n2Beijing Institute for General Artificial Intelligence  \n3Tianjin Conservatory of Music  \n4Beijing Electronic Science and Technology Institute  \n5Peking University  \n∗ Corresponding authors  \nAbstract  \nMusic aesthetic assessment is a challenging yet underexplored problem, requiring models to capture fine-grained, multi-dimensional human perceptual judgments.  \nProgress in this area has been limited by the lack of large-scale datasets with structured aesthetic annotations.  \nWe introduce MADB, a large-scale dataset and benchmark comprising 9,999 tracks annotated by 30 trained annotators. Each track is rated by around 10 annotators across 10 perceptual dimensions and one overall score, with additional textual comments for multimodal analysis.  \nWe establish a unified evaluation framework over multiple pretrained models.  \nResults reveal substantial gaps between model predictions and human judgments, exposing key limitations of current approaches.  \nMADB provides a new benchmark for human-aligned music understanding. Project page: [https://github.com/knownree/madb](https://github.com/knownree/madb)  \nFigure 1: Annotation examples  \nPreprint.  \n1 Introduction  \nThe rapid development of generative music models Agostinelli et al. [2023], Lei et al. [2025], Yuan et al. [2025] has led to a surge in AI-generated music, creating an urgent need for automatic evaluation aligned with human aesthetic preferences. The rapid expansion of AI-generated music not only creates diverse application scenarios for automatic aesthetic evaluation, but also elevates it to a critical component in modern music generation pipelines, with applications in content filtering, recommendation, and reinforcement learning from human feedback (RLHF) .  \nDespite these advances, current models often fail to produce music that aligns with human expectations, exhibiting issues such as structural incoherence and limited expressiveness Agostinelli et al.[2023], Copet et al. [2024] . This gap highlights the need for reliable aesthetic evaluation models that can accurately reflect human perception.  \nMusic aesthetic assessment is inherently challenging. It is subjective and exhibits substantial interindividual variability, while also requiring the modeling of relatively stable and generalizable criteria grounded in domain knowledge. Moreover, aesthetic evaluation in music relies heavily on expertise: trained musicians can provide fine-grained and technically grounded assessments, explaining not only whether a piece is preferred but also why it is perceived as aesthetically effective or flawed. This dual requirement of subjectivity and expertise makes large-scale, high-quality annotation particularly challenging.  \nHowever, existing datasets for music aesthetic evaluation remain limited in scale, number of annotators, and coverage of perceptual dimensions, and often rely on single-score annotations without richer supervision such as multi-dimensional ratings or textual feedback.  \nTo address these challenges, we make the following contributions:  \nA multidimensional music aesthetic annotation framework. We define an evaluation framework with one overall score and 10 fine-grained perceptual dimensions, supported by annotation guidelines to ensure consistency.  \nA large-scale music aesthetics dataset and benchmark. We construct MADB, a dataset of 9999 tracks annotated by trained annotators, each rated by 9–11 annotators across all dimensions, with additional textual comments.  \nA unified benchmark for music aesthetic assessment. We evaluate multiple pretrained models, including CLAP-based a","cbCaicceTCNccfpK","https://ap.wps.com/l/cbCaicceTCNccfpK","pdf",2483508,1,15,"English","en",105,"# Introduction\n# Related Work\n## Music Aesthetic Evaluation and Datasets\n## Music Representation Learning","[{\"question\":\"What problem does MADB address in music generation and evaluation?\",\"answer\":\"MADB targets the need for automatic music evaluation aligned with human aesthetic preferences, where current models often fail to match human expectations and produce music with issues like structural incoherence or limited expressiveness.\"},{\"question\":\"How is MADB annotated and what does each track include?\",\"answer\":\"MADB contains 9,999 tracks annotated by 30 trained annotators. Each track is rated by roughly 9–11 annotators across 10 perceptual dimensions plus one overall score, with additional textual comments for richer analysis.\"},{\"question\":\"What does the paper do to evaluate existing music aesthetic models?\",\"answer\":\"The paper proposes a unified evaluation framework across multiple pretrained models, including CLAP-based approaches, to compare model predictions against human judgments and highlight gaps in captured aesthetic information.\"}]",1784193577,38,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"madb-a-large-scale-music-aesthetics-dataset-with-professional-and-multi-dimensional-annotations","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/madb-a-large-scale-music-aesthetics-dataset-with-professional-and-multi-dimensional-annotations/84164/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does MADB address in music generation and evaluation?","Question",{"text":75,"@type":76},"MADB targets the need for automatic music evaluation aligned with human aesthetic preferences, where current models often fail to match human expectations and produce music with issues like structural incoherence or limited expressiveness.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is MADB annotated and what does each track include?",{"text":80,"@type":76},"MADB contains 9,999 tracks annotated by 30 trained annotators. Each track is rated by roughly 9–11 annotators across 10 perceptual dimensions plus one overall score, with additional textual comments for richer analysis.",{"name":82,"@type":73,"acceptedAnswer":83},"What does the paper do to evaluate existing music aesthetic models?",{"text":84,"@type":76},"The paper proposes a unified evaluation framework across multiple pretrained models, including CLAP-based approaches, to compare model predictions against human judgments and highlight gaps in captured aesthetic information.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]