{"id":"https://openalex.org/W2075180943","doi":"https://doi.org/10.1145/1101149.1101293","title":"Multimodal content-based structure analysis of karaoke music","display_name":"Multimodal content-based structure analysis of karaoke music","publication_year":2005,"publication_date":"2005-11-06","ids":{"openalex":"https://openalex.org/W2075180943","doi":"https://doi.org/10.1145/1101149.1101293","mag":"2075180943"},"language":"en","primary_location":{"id":"doi:10.1145/1101149.1101293","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1101149.1101293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th annual ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100833236","display_name":"Yongwei Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yongwei Zhu","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078467158","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0001-9520-4273"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102908901","display_name":"Qibin Sun","orcid":"https://orcid.org/0000-0002-6789-7460"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qibin Sun","raw_affiliation_strings":["Institute for Infocomm Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"638","last_page":"647"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T11439","display_name":"Video Analysis and Summarization","score":0.980400025844574,"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/T10860","display_name":"Speech and Audio Processing","score":0.9314000010490417,"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/lyrics","display_name":"Lyrics","score":0.9679242372512817},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8204171657562256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.766579270362854},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.634138286113739},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.5279207229614258},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4811724126338959},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3821178078651428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.330206036567688},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.13307541608810425},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1200580894947052},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10166943073272705}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9679242372512817},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8204171657562256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766579270362854},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.634138286113739},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5279207229614258},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4811724126338959},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3821178078651428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.330206036567688},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.13307541608810425},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1200580894947052},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10166943073272705},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1101149.1101293","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1101149.1101293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th annual ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.93.8423","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.93.8423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ctr.columbia.edu/~qibin/papers/qibin2005_acmmm.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1492953952","https://openalex.org/W1590108943","https://openalex.org/W2029263174","https://openalex.org/W2044916317","https://openalex.org/W2076608692","https://openalex.org/W2090874155","https://openalex.org/W2104098931","https://openalex.org/W2114449851","https://openalex.org/W2114640443","https://openalex.org/W2117586922","https://openalex.org/W2123603018","https://openalex.org/W2130976598","https://openalex.org/W2134096203","https://openalex.org/W2142575067","https://openalex.org/W2143235280"],"related_works":["https://openalex.org/W2378183644","https://openalex.org/W2287414930","https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674","https://openalex.org/W1975359510","https://openalex.org/W3110605476"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,40,116],"novel":[4,41,94],"approach":[5,161],"for":[6,162],"content-based":[7],"analysis":[8,97,165],"of":[9,51,62,115,133],"karaoke":[10,130],"music,":[11],"which":[12],"utilizes":[13],"multimodal":[14,160],"contents":[15],"including":[16],"synchronized":[17,68],"lyrics":[18,52,100,121,150],"text":[19,43,53,101,142],"from":[20,54],"the":[21,34,49,55,60,70,76,82,86,111,120,149,158,171],"video":[22,42,56,141],"channel":[23],"and":[24,58,102,113,118,147,157],"original":[25,77],"singing":[26,78,123],"audio":[27,32,36,88,103,179],"as":[28,30],"well":[29],"accompaniment":[31],"in":[33],"two":[35,87],"channels.":[37],"We":[38],"proposed":[39,107,140,159],"extraction":[44,143],"technique":[45,73,144],"to":[46,69,108],"accurately":[47],"segment":[48,119,148],"bitmaps":[50],"frames":[57],"track":[59],"time":[61],"its":[63],"color":[64],"changes":[65],"that":[66,74,138,174],"are":[67,175],"music.":[71],"A":[72,93],"characterizes":[75],"voice":[79],"by":[80],"analyzing":[81],"volume":[83],"balance":[84],"between":[85],"channels":[89],"is":[90,105],"also":[91],"proposed.":[92],"music":[95,131,163],"structure":[96,164],"method":[98,166],"using":[99],"content":[104,180],"then":[106],"precisely":[109],"identify":[110],"verses":[112],"choruses":[114],"song,":[117],"into":[122],"phrases.":[124],"Experimental":[125],"results":[126],"based":[127,176],"on":[128,178],"20":[129],"titles":[132],"difference":[134],"languages":[135],"have":[136],"shown":[137],"our":[139],"can":[145],"detect":[146],"texts":[151],"with":[152],"accuracy":[153],"higher":[154],"than":[155,170],"90%,":[156],"has":[167],"better":[168],"performance":[169],"previous":[172],"methods":[173],"only":[177],"analysis.":[181]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
