{"id":"https://openalex.org/W1992058582","doi":"https://doi.org/10.1145/2733373.2806379","title":"Octave-dependent Probabilistic Latent Semantic Analysis to Chorus Detection of Popular Song","display_name":"Octave-dependent Probabilistic Latent Semantic Analysis to Chorus Detection of Popular Song","publication_year":2015,"publication_date":"2015-10-13","ids":{"openalex":"https://openalex.org/W1992058582","doi":"https://doi.org/10.1145/2733373.2806379","mag":"1992058582"},"language":"en","primary_location":{"id":"doi:10.1145/2733373.2806379","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2733373.2806379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd 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/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":["Institute for Infocomm Research, A*STAR, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"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":"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":["Institute for Infocomm Research, A*STAR, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"979","last_page":"982"},"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":0.9897000193595886,"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":0.9883000254631042,"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/computer-science","display_name":"Computer science","score":0.7176231145858765},{"id":"https://openalex.org/keywords/octave","display_name":"Octave (electronics)","score":0.617450475692749},{"id":"https://openalex.org/keywords/chorus","display_name":"Chorus","score":0.559110701084137},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5461704134941101},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5302181839942932},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.5251507759094238},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.517693281173706},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.506234347820282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46119120717048645},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.43604668974876404},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12005263566970825},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09987980127334595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7176231145858765},{"id":"https://openalex.org/C85841341","wikidata":"https://www.wikidata.org/wiki/Q1135984","display_name":"Octave (electronics)","level":2,"score":0.617450475692749},{"id":"https://openalex.org/C2780832652","wikidata":"https://www.wikidata.org/wiki/Q5105266","display_name":"Chorus","level":2,"score":0.559110701084137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5461704134941101},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5302181839942932},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.5251507759094238},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.517693281173706},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.506234347820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46119120717048645},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.43604668974876404},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12005263566970825},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09987980127334595},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"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/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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2733373.2806379","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2733373.2806379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"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/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/W2142575067","https://openalex.org/W2169719929","https://openalex.org/W2340423008","https://openalex.org/W2406901689","https://openalex.org/W2465080433","https://openalex.org/W3216878400","https://openalex.org/W4233135949","https://openalex.org/W6605290772"],"related_works":["https://openalex.org/W2809745188","https://openalex.org/W2494818933","https://openalex.org/W2475648064","https://openalex.org/W2349772854","https://openalex.org/W3152157429","https://openalex.org/W2364547139","https://openalex.org/W2139934687","https://openalex.org/W2357558268","https://openalex.org/W3211508905","https://openalex.org/W2394476589"],"abstract_inverted_index":{"Content":[0],"representation":[1],"of":[2,9,47,72,107,112],"music":[3,10,93],"signal":[4],"is":[5,50,62,102,127],"an":[6],"essential":[7],"part":[8],"information":[11,86],"retrieval":[12],"applications,":[13],"e.g.":[14],"chorus":[15,105],"detection,":[16],"genre":[17],"classification,":[18],"etc.":[19],"In":[20,57,110],"the":[21,25,34,44,53,59,69,124,131],"paper,":[22],"we":[23],"propose":[24],"octave-dependent":[26],"probabilistic":[27],"latent":[28,35,60],"semantic":[29],"analysis":[30],"(OdPlsa)":[31],"to":[32,130],"discover":[33],"audio":[36,45],"patterns":[37],"(or":[38],"clusters)":[39],"through":[40],"spectral-temporal":[41],"analysis.":[42],"Then":[43],"content":[46],"each":[48],"segment":[49],"characterized":[51],"using":[52],"statistical":[54],"pattern":[55,61],"distribution.":[56],"OdPlsa,":[58],"modeled":[63],"by":[64],"multinomial":[65],"distribution":[66,71],"which":[67],"characterizes":[68],"magnitude":[70],"12-dimensional":[73],"pitch":[74],"class":[75],"profiles":[76],"over":[77],"a":[78,98],"temporal":[79],"window.":[80],"It":[81],"thus":[82],"effectively":[83],"models":[84],"melody":[85],"as":[87,89,97,117],"well":[88],"octave":[90],"relations":[91],"in":[92],"signal.":[94],"Its":[95],"efficiency":[96],"feature":[99],"extraction":[100],"technique":[101,126],"evaluated":[103],"on":[104],"detection":[106],"popular":[108],"songs.":[109],"terms":[111],"multiple":[113],"performance":[114],"metrics":[115],"such":[116],"boundary":[118],"accuracy,":[119],"precision,":[120],"recall":[121],"and":[122],"F1,":[123],"proposed":[125],"much":[128],"superior":[129],"widely":[132],"accepted":[133],"chroma":[134],"feature.":[135]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}