{"id":"https://openalex.org/W2089204011","doi":"https://doi.org/10.1109/icassp.2013.6637745","title":"Singing voice timbre classification of Chinese popular music","display_name":"Singing voice timbre classification of Chinese popular music","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2089204011","doi":"https://doi.org/10.1109/icassp.2013.6637745","mag":"2089204011"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6637745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6637745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5026888048","display_name":"Cheng-Ya Sha","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Cheng-Ya Sha","raw_affiliation_strings":["National Taiwan University, Taiwan","National Taiwan University Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Academia Sinica, China","Acad. Sinica, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica, China","institution_ids":[]},{"raw_affiliation_string":"Acad. Sinica, Taipei, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070648053","display_name":"Yu\u2010Ching Lin","orcid":"https://orcid.org/0000-0002-2318-8507"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu-Ching Lin","raw_affiliation_strings":["KKBOX, China","KKBOX, Taiwan"],"affiliations":[{"raw_affiliation_string":"KKBOX, China","institution_ids":[]},{"raw_affiliation_string":"KKBOX, Taiwan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046838550","display_name":"Homer H. Chen","orcid":"https://orcid.org/0000-0002-8795-1911"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Homer H. Chen","raw_affiliation_strings":["National Taiwan University, Taiwan","National Taiwan University Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5026888048"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":1.2768,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80930069,"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":"734","last_page":"738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9980999827384949,"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":0.9904000163078308,"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/timbre","display_name":"Timbre","score":0.935800313949585},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8684501647949219},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7295001745223999},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.7264420986175537},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7056562900543213},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6294214129447937},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5503324270248413},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4803706109523773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37157100439071655},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.1838665008544922},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1456393003463745},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.11336365342140198},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07722720503807068}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.935800313949585},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8684501647949219},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7295001745223999},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.7264420986175537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056562900543213},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6294214129447937},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5503324270248413},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4803706109523773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37157100439071655},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.1838665008544922},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1456393003463745},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.11336365342140198},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07722720503807068},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6637745","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6637745","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W65296863","https://openalex.org/W147964346","https://openalex.org/W178884067","https://openalex.org/W655376809","https://openalex.org/W1495061682","https://openalex.org/W1975929202","https://openalex.org/W1987759408","https://openalex.org/W2085662862","https://openalex.org/W2101151533","https://openalex.org/W2116373735","https://openalex.org/W2123169318","https://openalex.org/W2124867748","https://openalex.org/W2151455241","https://openalex.org/W2162200825","https://openalex.org/W2164098335","https://openalex.org/W2296199791","https://openalex.org/W2312612936","https://openalex.org/W2394506964","https://openalex.org/W2394955069","https://openalex.org/W2951443864","https://openalex.org/W3217467030","https://openalex.org/W4205952203","https://openalex.org/W6602647452","https://openalex.org/W6607294247","https://openalex.org/W6712043840","https://openalex.org/W6712099778","https://openalex.org/W6805302155"],"related_works":["https://openalex.org/W2373880408","https://openalex.org/W405661683","https://openalex.org/W2532856746","https://openalex.org/W238390473","https://openalex.org/W4288088492","https://openalex.org/W2982290989","https://openalex.org/W4394924759","https://openalex.org/W2119168266","https://openalex.org/W2886940211","https://openalex.org/W1850879794"],"abstract_inverted_index":{"Singing":[0],"voice":[1,34,96],"plays":[2],"an":[3,59],"important":[4],"role":[5],"in":[6,118,123],"the":[7,22,26,38,49,88,104,110],"listening":[8],"experience":[9],"of":[10,25,52,75,90,112],"music.":[11],"In":[12],"this":[13],"paper,":[14],"we":[15,30,62],"propose":[16,87],"to":[17,64],"classify":[18],"popular":[19,55],"music":[20],"by":[21],"timbre":[23,35,119],"quality":[24],"singing":[27,33,76,95],"voice.":[28],"Specifically,":[29],"adopt":[31],"six":[32],"classes":[36],"as":[37,80,98],"taxonomy":[39],"and":[40,67,71,82,94,108],"build":[41,58],"a":[42,73,124],"new":[43],"data":[44],"set,":[45],"KKTIC,":[46],"that":[47],"contains":[48],"expert":[50],"annotations":[51],"387":[53],"Chinese":[54],"songs.":[56],"To":[57],"automatic":[60],"classifier,":[61],"resort":[63],"signal":[65],"processing":[66],"machine":[68],"learning":[69],"techniques":[70],"extract":[72],"number":[74],"voice-related":[77],"features":[78,107],"such":[79],"vibrato":[81],"harmonic-to-noise":[83],"ratio.":[84],"We":[85],"also":[86],"use":[89],"vocal":[91],"segment":[92],"detection":[93],"separation":[97],"preprocessing":[99,114],"steps.":[100,115],"Our":[101],"evaluation":[102],"identifies":[103],"relevant":[105],"acoustic":[106],"validates":[109],"importance":[111],"these":[113],"The":[116],"accuracy":[117],"classification":[120],"reaches":[121],"79.84%":[122],"five-fold":[125],"stratified":[126],"cross":[127],"validation.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}