{"id":"https://openalex.org/W4393063447","doi":"https://doi.org/10.48550/arxiv.2403.13356","title":"KunquDB: An Attempt for Speaker Verification in the Chinese Opera Scenario","display_name":"KunquDB: An Attempt for Speaker Verification in the Chinese Opera Scenario","publication_year":2024,"publication_date":"2024-03-20","ids":{"openalex":"https://openalex.org/W4393063447","doi":"https://doi.org/10.48550/arxiv.2403.13356"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2403.13356","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.13356","pdf_url":"https://arxiv.org/pdf/2403.13356","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":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2403.13356","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102949163","display_name":"Huali Zhou","orcid":"https://orcid.org/0009-0008-6253-7379"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhou, Huali","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049403564","display_name":"Yuke Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Yuke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101321579","display_name":"Dong Liu","orcid":"https://orcid.org/0009-0002-4768-9039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Dong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351472","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-8197-6552"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ming","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102949163"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9768000245094299,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9768000245094299,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9409000277519226,"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/T11309","display_name":"Music and Audio Processing","score":0.902899980545044,"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/opera","display_name":"Opera","score":0.7995253801345825},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.7090516090393066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5048735737800598},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44933459162712097},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.42073532938957214},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2283688485622406},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.18046584725379944},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.10433760285377502},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.08339238166809082}],"concepts":[{"id":"https://openalex.org/C530479602","wikidata":"https://www.wikidata.org/wiki/Q1344","display_name":"Opera","level":2,"score":0.7995253801345825},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.7090516090393066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5048735737800598},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44933459162712097},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.42073532938957214},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2283688485622406},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.18046584725379944},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.10433760285377502},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.08339238166809082}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2403.13356","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.13356","pdf_url":"https://arxiv.org/pdf/2403.13356","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2403.13356","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2403.13356","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2403.13356","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2403.13356","pdf_url":"https://arxiv.org/pdf/2403.13356","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4393063447.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2353500159","https://openalex.org/W2386740010","https://openalex.org/W3011881386","https://openalex.org/W635637022","https://openalex.org/W2348070968","https://openalex.org/W2546089952","https://openalex.org/W2140022733","https://openalex.org/W2090976131","https://openalex.org/W1516392727"],"abstract_inverted_index":{"This":[0],"work":[1],"aims":[2],"to":[3],"promote":[4],"Chinese":[5,116],"opera":[6,97,129],"research":[7],"in":[8,87,115,128],"both":[9],"musical":[10],"and":[11,35,70,85,107,134],"speech":[12,132],"domains,":[13],"with":[14],"a":[15,26,78,160],"primary":[16],"focus":[17],"on":[18],"overcoming":[19],"the":[20,42,102,111],"data":[21],"limitations.":[22],"We":[23],"introduce":[24],"KunquDB,":[25],"relatively":[27],"large-scale,":[28],"well-annotated":[29],"audio-visual":[30],"dataset":[31,100],"comprising":[32],"339":[33],"speakers":[34],"128":[36],"hours":[37],"of":[38,113],"content.":[39],"Originating":[40],"from":[41],"Kunqu":[43],"Opera":[44],"Art":[45],"Canon":[46],"(Kunqu":[47],"yishu":[48],"dadian),":[49],"KunquDB":[50,76],"is":[51,153],"meticulously":[52],"structured":[53],"by":[54,72,146],"dialogue":[55],"lines,":[56],"providing":[57],"explicit":[58],"annotations":[59],"including":[60,90],"character":[61],"names,":[62,64],"speaker":[63],"gender":[65],"information,":[66],"vocal":[67,126,148],"manner":[68,149],"classifications,":[69],"accompanied":[71],"preliminary":[73],"text":[74],"transcriptions.":[75],"provides":[77],"versatile":[79],"foundation":[80],"for":[81,156],"role-centric":[82],"acoustic":[83],"studies":[84],"advancements":[86],"speech-related":[88],"research,":[89,98],"Automatic":[91],"Speaker":[92],"Verification":[93],"(ASV).":[94],"Beyond":[95],"enriching":[96],"this":[99],"bridges":[101],"gap":[103],"between":[104],"artistic":[105],"expression":[106],"technological":[108],"innovation.":[109],"Pioneering":[110],"exploration":[112],"ASV":[114],"opera,":[117],"we":[118],"construct":[119],"four":[120],"test":[121],"trials":[122],"considering":[123],"two":[124],"distinct":[125],"manners":[127],"voices:":[130],"stage":[131],"(ST)":[133],"singing":[135],"(S).":[136],"Implementing":[137],"domain":[138,143],"adaptation":[139],"methods":[140],"effectively":[141],"mitigates":[142],"mismatches":[144],"induced":[145],"these":[147],"variations":[150],"while":[151],"there":[152],"still":[154],"room":[155],"further":[157],"improvement":[158],"as":[159],"benchmark.":[161]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}
