{"id":"https://openalex.org/W4416799213","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249307","title":"Lyric-Aware Karaoke Background Video Selection Using Large Language Models and Moment Retrieval","display_name":"Lyric-Aware Karaoke Background Video Selection Using Large Language Models and Moment Retrieval","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799213","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249307"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109089501","display_name":"Tomoki Ariga","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Ariga","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091158809","display_name":"Jun Taniguchi","orcid":"https://orcid.org/0000-0002-0745-9290"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Taniguchi","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102017467","display_name":"Yosuke Higuchi","orcid":"https://orcid.org/0000-0003-4500-8957"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yosuke Higuchi","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115563209","display_name":"Sayaka Toma","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sayaka Toma","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kunihiro Abe","orcid":null},"institutions":[{"id":"https://openalex.org/I2802008203","display_name":"Daiichi University of Pharmacy","ror":"https://ror.org/03jvvjr23","country_code":"JP","type":"education","lineage":["https://openalex.org/I2802008203"]},{"id":"https://openalex.org/I4210104626","display_name":"Daiichi-Sankyo (Japan)","ror":"https://ror.org/027y26122","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210104626"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kunihiro Abe","raw_affiliation_strings":["DAIICHIKOSHO CO., LTD.,Tokyo,JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAIICHIKOSHO CO., LTD.,Tokyo,JAPAN","institution_ids":["https://openalex.org/I4210104626","https://openalex.org/I2802008203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115563212","display_name":"Rie Shigyo","orcid":null},"institutions":[{"id":"https://openalex.org/I2802008203","display_name":"Daiichi University of Pharmacy","ror":"https://ror.org/03jvvjr23","country_code":"JP","type":"education","lineage":["https://openalex.org/I2802008203"]},{"id":"https://openalex.org/I4210104626","display_name":"Daiichi-Sankyo (Japan)","ror":"https://ror.org/027y26122","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210104626"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rie Shigyo","raw_affiliation_strings":["DAIICHIKOSHO CO., LTD.,Tokyo,JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DAIICHIKOSHO CO., LTD.,Tokyo,JAPAN","institution_ids":["https://openalex.org/I4210104626","https://openalex.org/I2802008203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102081667","display_name":"Tetsuji Ogawa","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuji Ogawa","raw_affiliation_strings":["Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waseda University,Department of Communications and Computer Engineering,Tokyo,JAPAN","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33040113,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1497","last_page":"1502"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.8553000092506409,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.8553000092506409,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.10029999911785126,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0052999998442828655,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/selection","display_name":"Selection (genetic algorithm)","score":0.6947000026702881},{"id":"https://openalex.org/keywords/moment","display_name":"Moment (physics)","score":0.6201000213623047},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.5171999931335449},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5091999769210815},{"id":"https://openalex.org/keywords/video-retrieval","display_name":"Video retrieval","score":0.45320001244544983},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36309999227523804},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.36309999227523804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7885000109672546},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6947000026702881},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5472999811172485},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5091999769210815},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5042999982833862},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4187999963760376},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.3626999855041504},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C2780882242","wikidata":"https://www.wikidata.org/wiki/Q14235582","display_name":"Literal (mathematical logic)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.2556999921798706},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2111078031","https://openalex.org/W2159306398","https://openalex.org/W2962869524","https://openalex.org/W2963017553","https://openalex.org/W2997429269","https://openalex.org/W3205786327","https://openalex.org/W4322706621","https://openalex.org/W4386065689","https://openalex.org/W4386083094","https://openalex.org/W4390873341","https://openalex.org/W4415797147"],"related_works":[],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,20,44,54,115,120,157],"method":[3,149],"for":[4,87],"constructing":[5],"coherent":[6],"background":[7,139],"videos":[8,164],"by":[9],"automatically":[10],"selecting":[11],"and":[12,40,79],"combining":[13],"video":[14,95,147],"segments":[15,35,103],"that":[16],"semantically":[17],"align":[18],"with":[19,165],"song's":[21],"lyrics.":[22],"Rather":[23],"than":[24],"simply":[25],"visualizing":[26],"the":[27,31,33,51,63,91,100,109,129,137,144,162],"literal":[28],"content":[29],"of":[30,47,67,75,93,102,108,123,143],"lyrics,":[32],"selected":[34],"aim":[36],"to":[37,61,105,128],"convey":[38],"scenes":[39],"atmospheres":[41],"inferred":[42],"through":[43,156],"deeper":[45],"interpretation":[46,153],"their":[48],"meaning.":[49],"In":[50],"proposed":[52,145],"approach,":[53],"large":[55],"language":[56],"model":[57],"is":[58,126,154],"first":[59],"used":[60,167],"interpret":[62],"lyrics":[64],"in":[65,168],"terms":[66],"multiple":[68],"attributes,":[69],"such":[70],"as":[71,85],"characters,":[72],"season,":[73],"time":[74],"day,":[76],"weather,":[77],"location,":[78],"mood.":[80],"These":[81],"interpretations":[82],"then":[83],"serve":[84],"queries":[86],"moment":[88,124],"retrieval,":[89],"enabling":[90],"extraction":[92],"relevant":[94],"segments.":[96],"To":[97],"further":[98],"optimize":[99],"composition":[101],"assigned":[104],"each":[106],"part":[107],"song":[110],"(e.g.,":[111],"verse,":[112],"bridge,":[113],"chorus),":[114],"re-ranking":[116],"step":[117],"based":[118,150],"on":[119,151],"second":[121],"round":[122],"retrieval":[125,131],"applied":[127],"initial":[130],"results,":[132],"ensuring":[133],"global":[134],"consistency":[135],"across":[136],"final":[138],"video.":[140],"The":[141],"effectiveness":[142],"automatic":[146],"selection":[148],"lyric":[152],"validated":[155],"subjective":[158],"evaluation":[159],"experiment":[160],"comparing":[161],"generated":[163],"those":[166],"actual":[169],"karaoke":[170],"systems.":[171]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}
