{"id":"https://openalex.org/W2086357144","doi":"https://doi.org/10.1109/icassp.2014.6854595","title":"Vocal timbre analysis using latent Dirichlet allocation and cross-gender vocal timbre similarity","display_name":"Vocal timbre analysis using latent Dirichlet allocation and cross-gender vocal timbre similarity","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2086357144","doi":"https://doi.org/10.1109/icassp.2014.6854595","mag":"2086357144"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5039431216","display_name":"Tomoyasu Nakano","orcid":"https://orcid.org/0000-0001-8014-2209"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoyasu Nakano","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan","Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan","Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030650456","display_name":"Masataka Goto","orcid":"https://orcid.org/0000-0003-1167-0977"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Goto","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST), Japan","Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST), Japan","institution_ids":["https://openalex.org/I73613424"]},{"raw_affiliation_string":"Nat. Inst. of Adv. Ind. Sci. & Technol., AIST, Tsukuba, Japan","institution_ids":["https://openalex.org/I73613424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5202","last_page":"5206"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9955000281333923,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.9427438974380493},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.7861611247062683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6317247748374939},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.614449143409729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5057439804077148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.269825279712677},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.15937462449073792},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.05535084009170532}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9427438974380493},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.7861611247062683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6317247748374939},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.614449143409729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5057439804077148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.269825279712677},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.15937462449073792},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.05535084009170532},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2014.6854595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.645.9774","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.645.9774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/members/okuno/Public/ICASSP2014-Nakano.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.709.1234","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.709.1234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://staff.aist.go.jp/m.goto/PAPER/ICASSP2014nakano.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W16473758","https://openalex.org/W30895653","https://openalex.org/W49691034","https://openalex.org/W84787016","https://openalex.org/W99528949","https://openalex.org/W109946471","https://openalex.org/W125192980","https://openalex.org/W131779276","https://openalex.org/W135838486","https://openalex.org/W190299453","https://openalex.org/W774541572","https://openalex.org/W1037789387","https://openalex.org/W1496863122","https://openalex.org/W1582043709","https://openalex.org/W1588925254","https://openalex.org/W1605026219","https://openalex.org/W1880262756","https://openalex.org/W1916509133","https://openalex.org/W1935623011","https://openalex.org/W1964287530","https://openalex.org/W1965387202","https://openalex.org/W2001082470","https://openalex.org/W2023800933","https://openalex.org/W2053207518","https://openalex.org/W2072183986","https://openalex.org/W2072389495","https://openalex.org/W2104901100","https://openalex.org/W2124758433","https://openalex.org/W2126326123","https://openalex.org/W2128309385","https://openalex.org/W2128980425","https://openalex.org/W2144774941","https://openalex.org/W2152591660","https://openalex.org/W2158074454","https://openalex.org/W2160584856","https://openalex.org/W2168706009","https://openalex.org/W2170416904","https://openalex.org/W2288351922","https://openalex.org/W2294968229","https://openalex.org/W2296238881","https://openalex.org/W2296447391","https://openalex.org/W2394955069","https://openalex.org/W2397379877","https://openalex.org/W2398352100","https://openalex.org/W2403321691","https://openalex.org/W2405469863","https://openalex.org/W4237791300","https://openalex.org/W4285719527","https://openalex.org/W6604053933","https://openalex.org/W6604464690","https://openalex.org/W6605290772","https://openalex.org/W6605595087","https://openalex.org/W6607690849","https://openalex.org/W6622488751","https://openalex.org/W6627035393","https://openalex.org/W6635269905","https://openalex.org/W6636246373","https://openalex.org/W6639965443","https://openalex.org/W6640670638","https://openalex.org/W6679226638","https://openalex.org/W6684675790","https://openalex.org/W6696493858","https://openalex.org/W6697330893","https://openalex.org/W6697441424","https://openalex.org/W6697492545","https://openalex.org/W6712099778","https://openalex.org/W6712344852","https://openalex.org/W6712674617","https://openalex.org/W6713527549","https://openalex.org/W7039678360"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3126382579","https://openalex.org/W3107650560","https://openalex.org/W2406877384","https://openalex.org/W2595839522","https://openalex.org/W4315588616","https://openalex.org/W4317422773","https://openalex.org/W2810542905","https://openalex.org/W2124576126"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,95,101,117,126,146],"vocal":[4,36,56,65,131],"timbre":[5,57,132],"analysis":[6],"method":[7,115,127,154],"based":[8],"on":[9,22],"topic":[10,90],"modeling":[11],"using":[12,94,105],"latent":[13],"Dirichlet":[14],"allocation":[15],"(LDA).":[16],"Although":[17],"many":[18],"works":[19],"have":[20,29],"focused":[21],"analyzing":[23],"characteristics":[24,33],"of":[25,35,78,88,121,139],"singing":[26,43,141],"voices,":[27],"none":[28],"dealt":[30],"with":[31],"\u201clatent\u201d":[32],"(topics)":[34],"timbre,":[37],"which":[38],"are":[39],"shared":[40],"by":[41,83,93,109,134],"multiple":[42,79],"voices.":[44],"In":[45],"the":[46,86],"work":[47],"described":[48],"in":[49],"this":[50],"paper,":[51],"we":[52],"first":[53],"automatically":[54],"extracted":[55,68],"features":[58,69],"from":[59],"polyphonic":[60],"musical":[61],"audio":[62],"signals":[63,138],"including":[64],"sounds.":[66],"The":[67],"were":[70,81,91],"used":[71],"as":[72],"observed":[73],"data,":[74],"and":[75],"mixing":[76],"weights":[77],"topics":[80],"estimated":[82],"LDA.":[84],"Finally,":[85],"semantics":[87],"each":[89],"visualized":[92],"word-cloud-based":[96],"approach.":[97],"Experimental":[98,143],"results":[99,144],"for":[100,128,145],"singer":[102,148],"identification":[103],"task":[104,150],"36":[106],"songs":[107],"sung":[108],"12":[110],"singers":[111],"showed":[112,151],"that":[113,152],"our":[114,153],"achieved":[116],"mean":[118],"reciprocal":[119],"rank":[120],"0.86.":[122],"We":[123],"also":[124],"proposed":[125],"estimating":[129],"cross-gender":[130,147],"similarity":[133],"generating":[135],"pitch-shifted":[136,158],"(frequency-warped)":[137],"every":[140],"voice.":[142],"retrieval":[149],"discovered":[155],"interesting":[156],"similar":[157],"singers.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"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":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}