{"id":"https://openalex.org/W2188177872","doi":"https://doi.org/10.1109/mmsp.2015.7340798","title":"Popular song summarization using chorus section detection from audio signal","display_name":"Popular song summarization using chorus section detection from audio signal","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2188177872","doi":"https://doi.org/10.1109/mmsp.2015.7340798","mag":"2188177872"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2015.7340798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2015.7340798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP)","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/A5101707899","display_name":"Sheng Gao","orcid":"https://orcid.org/0000-0003-1591-0595"},"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":["A*STAR, Institute for Infocomm Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR, Institute for Infocomm Research, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"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":"Haizhou Li","raw_affiliation_strings":["A*STAR, Institute for Infocomm Research, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A*STAR, Institute for Infocomm Research, 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":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9944000244140625,"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":0.9940999746322632,"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/chorus","display_name":"Chorus","score":0.8576845526695251},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8504636287689209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7565711736679077},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6520400047302246},{"id":"https://openalex.org/keywords/octave","display_name":"Octave (electronics)","score":0.4949747920036316},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.47415679693222046},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4569036066532135},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4378066062927246},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4185541570186615},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4174911081790924},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38388511538505554},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.16579902172088623},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1596687138080597}],"concepts":[{"id":"https://openalex.org/C2780832652","wikidata":"https://www.wikidata.org/wiki/Q5105266","display_name":"Chorus","level":2,"score":0.8576845526695251},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8504636287689209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7565711736679077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6520400047302246},{"id":"https://openalex.org/C85841341","wikidata":"https://www.wikidata.org/wiki/Q1135984","display_name":"Octave (electronics)","level":2,"score":0.4949747920036316},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.47415679693222046},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4569036066532135},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4378066062927246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4185541570186615},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4174911081790924},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38388511538505554},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.16579902172088623},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1596687138080597},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2015.7340798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2015.7340798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320318547","display_name":"Baidu","ror":"https://ror.org/03vs3wt56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W37402343","https://openalex.org/W78743328","https://openalex.org/W131779276","https://openalex.org/W591222336","https://openalex.org/W1492953952","https://openalex.org/W1500744329","https://openalex.org/W1560013842","https://openalex.org/W1589362500","https://openalex.org/W1998937440","https://openalex.org/W2031767620","https://openalex.org/W2053049659","https://openalex.org/W2105676868","https://openalex.org/W2107743791","https://openalex.org/W2110681820","https://openalex.org/W2123991323","https://openalex.org/W2130976598","https://openalex.org/W2138452642","https://openalex.org/W2142575067","https://openalex.org/W2169719929","https://openalex.org/W2340423008","https://openalex.org/W2406901689","https://openalex.org/W3216878400","https://openalex.org/W4233135949","https://openalex.org/W6601496322","https://openalex.org/W6603169765","https://openalex.org/W6605290772","https://openalex.org/W6617581451","https://openalex.org/W6629394414","https://openalex.org/W6635107798","https://openalex.org/W6681234060","https://openalex.org/W6703828811","https://openalex.org/W6713620424","https://openalex.org/W6804558690","https://openalex.org/W6968595903"],"related_works":["https://openalex.org/W2188177872","https://openalex.org/W2793122029","https://openalex.org/W1828907027","https://openalex.org/W2338027094","https://openalex.org/W2171257135","https://openalex.org/W2104157383","https://openalex.org/W1483526280","https://openalex.org/W1964925579","https://openalex.org/W4248010623","https://openalex.org/W2109142991"],"abstract_inverted_index":{"Music":[0],"signal":[1],"is":[2,53,62,116,143,172],"a":[3,42,58],"one-dimensional":[4],"temporal":[5],"sequence.":[6],"It":[7],"thus":[8],"incurs":[9],"difficulty":[10],"for":[11],"the":[12,17,25,28,31,37,46,49,56,66,71,75,84,91,98,104,119,123,130,144,159,169,176],"listeners":[13,26],"to":[14,35,44,64,175],"quickly":[15],"capturing":[16],"mostly":[18],"attracting":[19],"parts":[20],"in":[21],"popular":[22,67],"songs,":[23],"unless":[24],"play":[27],"song":[29,47,120],"until":[30],"ending.":[32],"In":[33,55,152],"order":[34],"improve":[36],"listening":[38],"experience,":[39],"music":[40,114,149],"summarization,":[41],"tool":[43],"summarize":[45,65],"using":[48],"most":[50],"attractive":[51],"sections,":[52,128],"needed.":[54],"paper,":[57],"system":[59,82,171],"and":[60,97,108,132,164],"method":[61],"presented":[63],"songs":[68],"by":[69],"detecting":[70],"chorus":[72,99,109,127,137],"sections":[73],"from":[74],"input":[76],"audio":[77,86],"signal.":[78],"The":[79,111],"proposed":[80,170],"summarization":[81,115],"uses":[83],"unique":[85],"feature":[87],"representation":[88],"method,":[89],"i.e.":[90,129],"octave-dependent":[92],"probabilistic":[93],"latent":[94],"semantic":[95],"analysis,":[96],"detection":[100],"algorithm":[101],"that":[102,168],"combines":[103],"repeated":[105],"segment":[106],"extraction":[107],"identification.":[110],"performance":[112],"of":[113,126,135,148,154],"evaluated":[117],"on":[118],"database":[121],"with":[122],"ground":[124],"truth":[125],"start":[131],"ending":[133],"time-stamp":[134],"each":[136],"section.":[138],"As":[139],"we":[140,166],"know,":[141],"it":[142],"first":[145],"systematically":[146],"evaluation":[147],"summary":[150],"performance.":[151],"terms":[153],"multiple":[155],"metrics":[156],"such":[157],"as":[158],"boundary":[160],"accuracy,":[161],"precision,":[162],"recall":[163],"F1,":[165],"show":[167],"much":[173],"superior":[174],"widely":[177],"accepted":[178],"methods.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
