{"id":"https://openalex.org/W7094947155","doi":"https://doi.org/10.1145/3746027.3758148","title":"Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model","display_name":"Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W7094947155","doi":"https://doi.org/10.1145/3746027.3758148"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758148","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.06999","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zihao Wang","orcid":"https://orcid.org/0000-0002-5613-3262"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zihao Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China and Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-5613-3262","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China and Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruibin Yuan","orcid":"https://orcid.org/0009-0002-0539-6916"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ruibin Yuan","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hongkong, China"],"raw_orcid":"https://orcid.org/0009-0002-0539-6916","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hongkong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ziqi Geng","orcid":"https://orcid.org/0009-0006-6467-8349"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziqi Geng","raw_affiliation_strings":["University of California, Berkeley, Berkeley, USA"],"raw_orcid":"https://orcid.org/0009-0006-6467-8349","affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hengjia Li","orcid":"https://orcid.org/0009-0007-6184-9437"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hengjia Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China and Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0009-0007-6184-9437","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China and Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xingwei Qu","orcid":"https://orcid.org/0000-0002-3265-7133"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xingwei Qu","raw_affiliation_strings":["University of Manchester, Manchester, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-3265-7133","affiliations":[{"raw_affiliation_string":"University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinyi Li","orcid":"https://orcid.org/0009-0008-1863-6476"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-1863-6476","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Songye Chen","orcid":"https://orcid.org/0009-0008-8401-2370"},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songye Chen","raw_affiliation_strings":["Mei KTV, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-8401-2370","affiliations":[{"raw_affiliation_string":"Mei KTV, Beijing, China","institution_ids":["https://openalex.org/I4210152823"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoying Fu","orcid":"https://orcid.org/0009-0008-8049-013X"},"institutions":[{"id":"https://openalex.org/I4210152823","display_name":"China Meat Research Centre","ror":"https://ror.org/05jc4yc89","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210152823"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoying Fu","raw_affiliation_strings":["Mei KTV, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-8049-013X","affiliations":[{"raw_affiliation_string":"Mei KTV, Beijing, China","institution_ids":["https://openalex.org/I4210152823"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Roger B. Dannenberg","orcid":"https://orcid.org/0000-0003-1823-9856"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roger B. Dannenberg","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0003-1823-9856","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kejun Zhang","orcid":"https://orcid.org/0000-0002-0778-2303"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kejun Zhang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China and Innovation Center of Yangtze River Delta, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0778-2303","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China and Innovation Center of Yangtze River Delta, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12227","last_page":"12236"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10978","display_name":"Prenatal Screening and Diagnostics","score":0.1152999997138977,"subfield":{"id":"https://openalex.org/subfields/2735","display_name":"Pediatrics, Perinatology and Child Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10978","display_name":"Prenatal Screening and Diagnostics","score":0.1152999997138977,"subfield":{"id":"https://openalex.org/subfields/2735","display_name":"Pediatrics, Perinatology and Child Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12552","display_name":"Fetal and Pediatric Neurological Disorders","score":0.038100000470876694,"subfield":{"id":"https://openalex.org/subfields/2735","display_name":"Pediatrics, Perinatology and Child Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11732","display_name":"Assisted Reproductive Technology and Twin Pregnancy","score":0.03139999881386757,"subfield":{"id":"https://openalex.org/subfields/2735","display_name":"Pediatrics, Perinatology and Child Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6588000059127808},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6050999760627747},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.49059998989105225},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4900999963283539},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.4399000108242035},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4163999855518341},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.3978999853134155},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3937000036239624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.714900016784668},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6588000059127808},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6050999760627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.52920001745224},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.49059998989105225},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4399000108242035},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43970000743865967},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38679999113082886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.383899986743927},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.3580999970436096},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3758148","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758148","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.06999","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.06999","pdf_url":"https://arxiv.org/pdf/2512.06999","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.06999","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.06999","pdf_url":"https://arxiv.org/pdf/2512.06999","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6358190178871155,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G8331642082","display_name":null,"funder_award_id":"No.62272409","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1973249776","https://openalex.org/W2048752878","https://openalex.org/W2089956847","https://openalex.org/W2890271810","https://openalex.org/W2890964092","https://openalex.org/W2936449501","https://openalex.org/W4304091524","https://openalex.org/W4372348289","https://openalex.org/W4386159990","https://openalex.org/W4386590352","https://openalex.org/W4401023691","https://openalex.org/W4403722087","https://openalex.org/W4408354677","https://openalex.org/W4412888548"],"related_works":[],"abstract_inverted_index":{"Automated":[0],"singing":[1],"assessment":[2],"is":[3],"crucial":[4],"for":[5,41,53],"education":[6],"and":[7,24,37,76,126],"entertainment.":[8],"However,":[9],"existing":[10],"systems":[11],"face":[12],"two":[13],"fundamental":[14],"limitations:":[15],"reliance":[16],"on":[17,35],"reference":[18],"tracks,":[19],"which":[20,144],"stifles":[21],"creative":[22],"expression,":[23,75],"the":[25,88,96,137],"simplification":[26],"of":[27,90,99],"complex":[28],"performances":[29],"into":[30],"non-diagnostic":[31],"scores":[32],"based":[33],"solely":[34],"pitch":[36],"rhythm.":[38],"We":[39],"advocate":[40],"a":[42,50,61,117,146],"shift":[43],"from":[44],"discriminative":[45],"to":[46,121,130,149],"descriptive":[47],"evaluation,":[48],"creating":[49],"complete":[51],"ecosystem":[52],"reference-free,":[54],"multi-dimensional":[55],"assessment.":[56],"First,":[57],"we":[58,109,135],"introduce":[59],"Sing-MD,":[60],"large-scale":[62],"dataset":[63],"annotated":[64],"by":[65],"experts":[66],"across":[67],"four":[68],"dimensions:":[69],"breath":[70],"control,":[71],"timbre":[72],"quality,":[73],"emotional":[74],"vocal":[77],"technique.":[78],"Our":[79],"analysis":[80],"reveals":[81],"significant":[82],"annotation":[83],"inconsistencies":[84],"among":[85],"experts,":[86],"challenging":[87],"validity":[89],"traditional":[91],"accuracy-based":[92],"metrics.":[93],"Second,":[94],"addressing":[95],"memory":[97],"limitations":[98],"Multimodal":[100],"Large":[101],"Language":[102],"Models":[103],"(MLLMs)":[104],"in":[105],"analyzing":[106],"full-length":[107],"songs,":[108],"propose":[110],"VocalVerse.":[111],"This":[112],"efficient":[113],"hybrid":[114],"architecture":[115],"leverages":[116],"lightweight":[118],"acoustic":[119],"encoder":[120],"model":[122],"global":[123],"performance":[124],"features":[125],"long-term":[127],"dependencies.":[128],"Third,":[129],"address":[131],"automated":[132],"metric":[133],"shortcomings,":[134],"establish":[136],"H-TPR":[138],"(Human-in-the-loop":[139],"Tiered":[140],"Perceptual":[141],"Ranking)":[142],"benchmark,":[143],"evaluates":[145],"model's":[147],"ability":[148],"generate":[150],"perceptually":[151],"valid":[152],"rankings":[153],"rather":[154],"than":[155],"predicting":[156],"noisy":[157],"ground-truth":[158],"scores.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}