{"id":"https://openalex.org/W1993667686","doi":"https://doi.org/10.1145/2448556.2448638","title":"Music segmentation and summarization based on self-similarity matrix","display_name":"Music segmentation and summarization based on self-similarity matrix","publication_year":2013,"publication_date":"2013-01-17","ids":{"openalex":"https://openalex.org/W1993667686","doi":"https://doi.org/10.1145/2448556.2448638","mag":"1993667686"},"language":"en","primary_location":{"id":"doi:10.1145/2448556.2448638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2448556.2448638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication","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/A5066524393","display_name":"Sanghoon Jun","orcid":"https://orcid.org/0000-0002-5971-8282"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sanghoon Jun","raw_affiliation_strings":["Korea University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071337745","display_name":"Eenjun Hwang","orcid":"https://orcid.org/0000-0002-0418-4092"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eenjun Hwang","raw_affiliation_strings":["Korea University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066524393"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.9576,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73649994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.998199999332428,"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":0.9765999913215637,"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/automatic-summarization","display_name":"Automatic summarization","score":0.6796981692314148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6538922190666199},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6197329163551331},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5973149538040161},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5866856575012207},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5360617637634277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49970269203186035},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4962671399116516},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.46911314129829407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44848430156707764},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44166359305381775},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15634912252426147}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6796981692314148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6538922190666199},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6197329163551331},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5973149538040161},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5866856575012207},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5360617637634277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49970269203186035},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4962671399116516},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.46911314129829407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44848430156707764},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44166359305381775},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15634912252426147},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2448556.2448638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2448556.2448638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Conference on Ubiquitous Information Management and Communication","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1134677040","display_name":null,"funder_award_id":"2012-0007202","funder_id":"https://openalex.org/F4320322349","funder_display_name":"Ministry of Education, Science and Technology"},{"id":"https://openalex.org/G2072907217","display_name":null,"funder_award_id":"NIPA-2012-H0301-12-3006","funder_id":"https://openalex.org/F4320322065","funder_display_name":"National IT Industry Promotion Agency"},{"id":"https://openalex.org/G8722385642","display_name":null,"funder_award_id":"NIPA-2012-H0301-12-3006","funder_id":"https://openalex.org/F4320321640","funder_display_name":"Ministry of Knowledge Economy"}],"funders":[{"id":"https://openalex.org/F4320321640","display_name":"Ministry of Knowledge Economy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320322065","display_name":"National IT Industry Promotion Agency","ror":"https://ror.org/026v53e29"},{"id":"https://openalex.org/F4320322349","display_name":"Ministry of Education, Science and Technology","ror":"https://ror.org/01p262204"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W15066456","https://openalex.org/W1492953952","https://openalex.org/W1556200975","https://openalex.org/W1560013842","https://openalex.org/W2008765103","https://openalex.org/W2043931684","https://openalex.org/W2106374173","https://openalex.org/W2108078375","https://openalex.org/W2119821739","https://openalex.org/W2133824856","https://openalex.org/W2142575067","https://openalex.org/W2165578912","https://openalex.org/W2168249484","https://openalex.org/W2169790300","https://openalex.org/W2294938120","https://openalex.org/W2407544556"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W4323520239","https://openalex.org/W4389760904","https://openalex.org/W2032548952"],"abstract_inverted_index":{"In":[0,71],"this":[1,72],"paper,":[2],"we":[3,21],"propose":[4],"a":[5,32,81,89,102,113],"new":[6],"method":[7,126],"for":[8,49],"segmenting":[9],"and":[10,30,69,108],"summarizing":[11],"music":[12,28,42,50,65,75,90,103,107,117],"based":[13],"on":[14],"its":[15],"structure":[16],"analysis.":[17],"To":[18],"do":[19],"that,":[20],"first":[22],"extract":[23],"timbre":[24],"feature":[25],"from":[26],"acoustic":[27],"signal":[29],"construct":[31],"self-similarity":[33],"matrix":[34],"that":[35,97],"shows":[36],"similarities":[37],"among":[38],"the":[39,57,98,106,116,121],"features":[40],"within":[41],"clip.":[43,118],"We":[44,95,119],"then":[45],"determine":[46],"candidate":[47],"boundaries":[48],"segmentation":[51],"by":[52,80],"tracking":[53],"standard":[54],"deviation":[55],"in":[56,64],"matrix.":[58],"Similar":[59],"segments":[60],"such":[61],"as":[62,112],"repetition":[63],"clip":[66,76,104],"are":[67],"clustered":[68],"merged.":[70],"way,":[73],"each":[74,86],"can":[77],"be":[78],"represented":[79],"sequence":[82],"of":[83,101,115,123],"states":[84],"where":[85],"state":[87],"represents":[88,105],"segment":[91,100],"with":[92],"similar":[93],"feature.":[94],"assume":[96],"longest":[99],"hence":[109],"use":[110],"it":[111],"summary":[114],"show":[120],"performance":[122],"our":[124],"proposed":[125],"through":[127],"experiments.":[128]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}