{"id":"https://openalex.org/W4415539240","doi":"https://doi.org/10.1145/3746027.3758210","title":"Multi-Accent Mandarin Dry-Vocal Singing Dataset: Benchmark for Singing Accent Recognition","display_name":"Multi-Accent Mandarin Dry-Vocal Singing Dataset: Benchmark for Singing Accent Recognition","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539240","doi":"https://doi.org/10.1145/3746027.3758210"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758210","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758210","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/2512.07005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100413090","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":"https://openalex.org/A5007662123","display_name":"Shulei Ji","orcid":"https://orcid.org/0000-0002-9908-136X"},"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":"Shulei Ji","raw_affiliation_strings":["Zhejiang University, Hangzhou, China and Innovation Center of Yangtze River Delta, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9908-136X","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"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Le Ma","orcid":"https://orcid.org/0009-0001-2266-4209"},"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":"Le Ma","raw_affiliation_strings":["Zhejiang University, Hang Zhou, China"],"raw_orcid":"https://orcid.org/0009-0001-2266-4209","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hang Zhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhang Jin","orcid":"https://orcid.org/0009-0002-4715-9011"},"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":"Yuhang Jin","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-4715-9011","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103014224","display_name":"Shun Lei","orcid":"https://orcid.org/0000-0003-3597-3913"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shun Lei","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3597-3913","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046262750","display_name":"Jianyi Chen","orcid":"https://orcid.org/0009-0002-7690-5570"},"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":"Jianyi Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hongkong, China"],"raw_orcid":"https://orcid.org/0009-0002-7690-5570","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hongkong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113071013","display_name":"Haoying Fu","orcid":null},"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":"https://openalex.org/A5000265897","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":"https://openalex.org/A5101577175","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, Hang Zhou, Zhe Jiang, 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, Hang Zhou, Zhe Jiang, China and Innovation Center of Yangtze River Delta, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12714","last_page":"12721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8928999900817871},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8062000274658203},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.7972000241279602},{"id":"https://openalex.org/keywords/octave","display_name":"Octave (electronics)","score":0.4675999879837036},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3885999917984009},{"id":"https://openalex.org/keywords/morpheme","display_name":"Morpheme","score":0.2939000129699707}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8928999900817871},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8062000274658203},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.7972000241279602},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6251999735832214},{"id":"https://openalex.org/C85841341","wikidata":"https://www.wikidata.org/wiki/Q1135984","display_name":"Octave (electronics)","level":2,"score":0.4675999879837036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4659000039100647},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35850000381469727},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3244999945163727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C173988693","wikidata":"https://www.wikidata.org/wiki/Q678132","display_name":"Phonation","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.26989999413490295}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3758210","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758210","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:2512.07005","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.07005","pdf_url":"https://arxiv.org/pdf/2512.07005","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:2512.07005","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.07005","pdf_url":"https://arxiv.org/pdf/2512.07005","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":[],"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":12,"referenced_works":["https://openalex.org/W2526050071","https://openalex.org/W2747874407","https://openalex.org/W2963242190","https://openalex.org/W3163132306","https://openalex.org/W3212387720","https://openalex.org/W4206908380","https://openalex.org/W4280572880","https://openalex.org/W4285345683","https://openalex.org/W4386590352","https://openalex.org/W4388642341","https://openalex.org/W4403722087","https://openalex.org/W4412888548"],"related_works":[],"abstract_inverted_index":{"Singing":[0,49],"accent":[1,8,38,108,128],"research":[2],"is":[3],"underexplored":[4],"compared":[5],"to":[6,12,73],"speech":[7,116],"studies,":[9],"primarily":[10],"due":[11],"the":[13,29,45,131],"scarcity":[14],"of":[15,57,78,133],"suitable":[16],"datasets.":[17],"Existing":[18],"singing":[19,107,119,127],"datasets":[20],"often":[21,35],"suffer":[22],"from":[23,28,61],"detail":[24],"loss,":[25],"frequently":[26],"resulting":[27],"vocal-instrumental":[30],"separation":[31],"process.":[32],"Additionally,":[33],"they":[34,86],"lack":[36],"regional":[37],"annotations.":[39],"To":[40],"address":[41],"this,":[42],"we":[43,122],"introduce":[44],"Multi-Accent":[46],"Mandarin":[47,64,93],"Dry-Vocal":[48],"Dataset":[50],"(MADVSD).":[51],"MADVSD":[52,102],"comprises":[53],"over":[54],"670":[55],"hours":[56],"dry":[58],"vocal":[59],"recordings":[60],"4,206":[62],"native":[63,84],"speakers":[65],"across":[66],"nine":[67],"distinct":[68],"Chinese":[69],"regions.":[70],"In":[71],"addition":[72],"each":[74],"participant":[75],"recording":[76],"audio":[77],"three":[79],"popular":[80],"songs":[81],"in":[82,106,118,135],"their":[83],"accent,":[85],"also":[87],"recorded":[88],"phonetic":[89,141],"exercises":[90],"covering":[91],"all":[92],"vowels":[94,134],"and":[95,129],"a":[96],"full":[97],"octave":[98],"range.":[99],"We":[100],"validated":[101],"through":[103],"benchmark":[104],"experiments":[105],"recognition,":[109],"demonstrating":[110],"its":[111],"utility":[112],"for":[113],"evaluating":[114],"state-of-the-art":[115],"models":[117],"contexts.":[120],"Furthermore,":[121],"explored":[123],"dialectal":[124],"influences":[125],"on":[126],"analyzed":[130],"role":[132],"accentual":[136],"variations,":[137],"leveraging":[138],"MADVSD's":[139],"unique":[140],"exercises.":[142]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}
