{"id":"https://openalex.org/W2098448993","doi":"https://doi.org/10.1109/icme.2005.1521620","title":"Extracting Vocal Melody from Karaoke Music Audio","display_name":"Extracting Vocal Melody from Karaoke Music Audio","publication_year":2005,"publication_date":"2005-10-24","ids":{"openalex":"https://openalex.org/W2098448993","doi":"https://doi.org/10.1109/icme.2005.1521620","mag":"2098448993"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2005.1521620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","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/A5108222002","display_name":"Y. Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":["ASTAR Institute of Infocomm Research, Singapore","Institute for Infocomm Research, A*STAR,Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASTAR Institute of Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR,Singapore,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sheng Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"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":"Sheng Gao","raw_affiliation_strings":["ASTAR Institute of Infocomm Research, Singapore","Institute for Infocomm Research, A*STAR,Singapore,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ASTAR Institute of Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR,Singapore,Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1110","last_page":"1113"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9950000047683716,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9911999702453613,"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/speech-recognition","display_name":"Speech recognition","score":0.7890851497650146},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7886847257614136},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.740774393081665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6767905354499817},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5983520746231079},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.5809335112571716},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47170495986938477},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.46891531348228455},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4657367765903473},{"id":"https://openalex.org/keywords/musical-instrument","display_name":"Musical instrument","score":0.43414920568466187},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.42481529712677},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.29266026616096497},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.2598150074481964},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.20384091138839722},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.18931448459625244},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09812155365943909},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.08398878574371338}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7890851497650146},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7886847257614136},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.740774393081665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6767905354499817},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5983520746231079},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.5809335112571716},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47170495986938477},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.46891531348228455},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4657367765903473},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.43414920568466187},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.42481529712677},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.29266026616096497},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2598150074481964},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.20384091138839722},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.18931448459625244},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09812155365943909},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.08398878574371338},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2005.1521620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W200190320","https://openalex.org/W1958993123","https://openalex.org/W2076608692","https://openalex.org/W2129905846","https://openalex.org/W2131913731","https://openalex.org/W2141119838","https://openalex.org/W2143235280","https://openalex.org/W6608199584","https://openalex.org/W6640989775","https://openalex.org/W6679816892","https://openalex.org/W6680494108"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W2061360790","https://openalex.org/W4243888788","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2769884427"],"abstract_inverted_index":{"Extracting":[0],"the":[1,32,36,50,57,61,74,85,89,99,102,106,113,118,136,146,158,161],"melody":[2,19,29,123,172],"from":[3,21,55,73],"polyphonic":[4],"musical":[5],"audio":[6,53],"is":[7,77,92,109,124,168,178],"a":[8,127],"nontrivial":[9],"research":[10],"problem.":[11],"This":[12,132],"paper":[13],"presents":[14],"an":[15,176],"approach":[16],"for":[17,45,145],"vocal":[18],"extraction":[20,166],"dual":[22],"channel":[23,59,64],"Karaoke":[24,153],"music":[25,47,154],"audio.":[26],"The":[27,67,121,164],"extracted":[28,72,122],"corresponds":[30],"to":[31,105],"singing":[33,107,147],"voice":[34,108],"in":[35,79,98,175],"original":[37,62],"performance":[38,63,143,159],"channel,":[39],"which":[40,76],"can":[41],"then":[42],"be":[43],"used":[44],"melody-based":[46],"retrieval.":[48],"In":[49],"proposed":[51,162],"technique,":[52],"signals":[54],"both":[56],"accompaniment":[58,141],"and":[60,171],"are":[65,70],"analyzed.":[66],"note":[68,114],"partials":[69],"firstly":[71],"signal,":[75],"represented":[78,125],"constant-Q":[80],"transform":[81],"frequency":[82],"domain.":[83],"Then":[84],"volume":[86],"balance":[87],"between":[88,117],"two":[90,119,137],"channels":[91,138],"estimated":[93],"based":[94,111],"on":[95,112,151],"signal":[96],"approximation":[97],"sub-bands.":[100],"Finally,":[101],"pitch":[103,130,165],"corresponding":[104],"identified":[110],"partial":[115],"differences":[116],"channels.":[120],"as":[126],"sequence":[128],"of":[129,160],"values.":[131],"technique":[133],"assumes":[134],"that":[135],"have":[139],"similar":[140],"instrument":[142],"except":[144],"voices.":[148],"Experimental":[149],"result":[150],"40":[152],"audios":[155],"has":[156],"shown":[157],"technique.":[163],"rate":[167],"above":[169],"70%":[170],"retrieval":[173],"accuracy":[174],"800-tune-database":[177],"90%.":[179]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
