{"id":"https://openalex.org/W99956014","doi":"https://doi.org/10.5281/zenodo.1417845","title":"Automatic Detection Of Vocal Segments In Popular Songs.","display_name":"Automatic Detection Of Vocal Segments In Popular Songs.","publication_year":2004,"publication_date":"2004-10-10","ids":{"openalex":"https://openalex.org/W99956014","doi":"https://doi.org/10.5281/zenodo.1417845","mag":"99956014"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.111.2080","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.111.2080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ismir2004.ismir.net/proceedings/p028-page-138-paper183.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/1417846","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050008407","display_name":"Tin Lay Nwe","orcid":"https://orcid.org/0000-0003-1111-580X","observed_orcids":["https://orcid.org/0000-0003-1111-580X"]},"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"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nwe, Tin Lay","raw_affiliation_strings":["Agency for Science, Technology and Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100423435","display_name":"Ye Wang","orcid":"https://orcid.org/0000-0002-0123-1260","observed_orcids":["https://orcid.org/0000-0002-0123-1260","https://orcid.org/0000-0002-4577-8137","https://orcid.org/0009-0007-1897-0637","https://orcid.org/0009-0007-7510-4882"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wang, Ye","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9561,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.93165906,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":9.999999747378752e-05,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/popular-music","display_name":"popular music","score":0.7839999794960022},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.777999997138977},{"id":"https://openalex.org/keywords/bootstrap-method","display_name":"bootstrapping","score":0.7490000128746033},{"id":"https://openalex.org/keywords/acoustic-characteristics","display_name":"acoustic features","score":0.9369999766349792},{"id":"https://openalex.org/keywords/music-signal-analysis","display_name":"music signal analysis","score":0.5099999904632568}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8605368137359619},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7751978635787964},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7357037663459778},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5752315521240234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5601314306259155},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5459399223327637},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5129015445709229}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.111.2080","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.111.2080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ismir2004.ismir.net/proceedings/p028-page-138-paper183.pdf","raw_type":"text"},{"id":"pmh:oai:zenodo.org:1417846","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/1417846","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"mag:99956014","doi":null,"is_oa":false,"landing_page_url":"https://www.comp.nus.edu.sg/~wangye/papers/1.Audio_and_Music_Analysis_and_Retrieval/2004_Automatic_Detection_of_Vocal_Segments_in_Popular_Songs.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420076","display_name":"International Symposium/Conference on Music Information Retrieval","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Symposium/Conference on Music Information Retrieval","raw_type":null},{"id":"doi:10.5281/zenodo.1417845","doi":"https://doi.org/10.5281/zenodo.1417845","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.1417845","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5281/zenodo.1417846","doi":"https://doi.org/10.5281/zenodo.1417846","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.1417846","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:1417846","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/1417846","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2708685","https://openalex.org/W55723365","https://openalex.org/W173389330","https://openalex.org/W1560013842","https://openalex.org/W1570504315","https://openalex.org/W1833279920","https://openalex.org/W1945892259","https://openalex.org/W2112446559","https://openalex.org/W2124867748","https://openalex.org/W2157569565","https://openalex.org/W2158510078","https://openalex.org/W2165320163","https://openalex.org/W2798890691","https://openalex.org/W6911903932"],"related_works":["https://openalex.org/W22010227","https://openalex.org/W2989404121","https://openalex.org/W1565212776","https://openalex.org/W2295946864","https://openalex.org/W648096282","https://openalex.org/W2058753153","https://openalex.org/W7214684553","https://openalex.org/W157162596","https://openalex.org/W3217392809","https://openalex.org/W180220758"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,97],"technique":[4,21],"for":[5,42,58,69,89],"the":[6,36,84,105,108],"automatic":[7,79],"classification":[8,91],"of":[9,99,107],"vocal":[10,30,43],"and":[11,31,44],"non-vocal":[12,32,45],"regions":[13],"in":[14],"an":[15,63,78],"acoustic":[16,23],"musical":[17],"signal.":[18],"The":[19],"proposed":[20,109],"uses":[22],"features":[24],"which":[25,54,82],"are":[26],"suitable":[27],"to":[28,49],"distinguish":[29],"signals.":[33],"We":[34],"employ":[35,55,77],"Hidden":[37],"Markov":[38],"Model":[39],"(HMM)":[40],"classifier":[41],"classification.":[46],"In":[47,74],"contrast":[48],"conventional":[50],"HMM":[51,64],"training":[52],"methods":[53],"one":[56],"model":[57,65],"each":[59],"class,":[60],"we":[61,76],"create":[62],"space":[66],"(multi-model":[67],"HMMs)":[68],"segmentation":[70],"with":[71],"improved":[72],"accuracy.":[73,92],"addition,":[75],"bootstrapping":[80],"process":[81],"adapts":[83],"test":[85],"song\u2019s":[86],"own":[87],"models":[88],"better":[90],"Experimental":[93],"evaluations":[94],"conducted":[95],"on":[96],"database":[98],"20":[100],"popular":[101],"music":[102],"songs":[103],"show":[104],"validity":[106],"approach.":[110],"1.":[111]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}