{"id":"https://openalex.org/W4388117839","doi":"https://doi.org/10.23919/eusipco58844.2023.10290004","title":"PrimaDNN\u2019:A Characteristics-Aware DNN Customization for Singing Technique Detection","display_name":"PrimaDNN\u2019:A Characteristics-Aware DNN Customization for Singing Technique Detection","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388117839","doi":"https://doi.org/10.23919/eusipco58844.2023.10290004"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10290004","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10290004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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/A5101025232","display_name":"Yuya Yamamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuya Yamamoto","raw_affiliation_strings":["Doctoral Program in Informatics University of Tsukuba,Ibaraki,Japan","Doctoral Program in Informatics University of Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"Doctoral Program in Informatics University of Tsukuba,Ibaraki,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"Doctoral Program in Informatics University of Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056437111","display_name":"Juhan Nam","orcid":"https://orcid.org/0000-0003-2664-2119"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhan Nam","raw_affiliation_strings":["Graduate School of Culture Technology KAIST,Daejeon,South Korea","Graduate School of Culture Technology KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Culture Technology KAIST,Daejeon,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Graduate School of Culture Technology KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008403512","display_name":"Hiroko Terasawa","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroko Terasawa","raw_affiliation_strings":["Doctoral Program in Informatics University of Tsukuba,Ibaraki,Japan","Doctoral Program in Informatics University of Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"Doctoral Program in Informatics University of Tsukuba,Ibaraki,Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"Doctoral Program in Informatics University of Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101025232"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":0.2038,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46522692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"406","last_page":"410"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9965000152587891,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9911999702453613,"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/singing","display_name":"Singing","score":0.8809863328933716},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.8222665190696716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7867943644523621},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6929833292961121},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6516833305358887},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6333639621734619},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.5616668462753296},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45277833938598633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4199775755405426},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.41600823402404785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32999998331069946},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2124418020248413}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8809863328933716},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8222665190696716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7867943644523621},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6929833292961121},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6516833305358887},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6333639621734619},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.5616668462753296},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45277833938598633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4199775755405426},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.41600823402404785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32999998331069946},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2124418020248413},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10290004","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10290004","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2239141610","https://openalex.org/W2408239454","https://openalex.org/W2502312327","https://openalex.org/W2752782242","https://openalex.org/W2810934215","https://openalex.org/W2884366600","https://openalex.org/W2962866891","https://openalex.org/W2963351448","https://openalex.org/W2963451564","https://openalex.org/W2968917279","https://openalex.org/W2972659941","https://openalex.org/W3016099302","https://openalex.org/W3024869864","https://openalex.org/W3036601975","https://openalex.org/W3049446265","https://openalex.org/W3117235375","https://openalex.org/W3144907487","https://openalex.org/W3152594694","https://openalex.org/W3160333138","https://openalex.org/W4226300471","https://openalex.org/W4307934381","https://openalex.org/W6724804524","https://openalex.org/W6767164110","https://openalex.org/W6780218876","https://openalex.org/W6804117339","https://openalex.org/W6846452521"],"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":{"Professional":[0],"vocalists":[1],"modulate":[2],"their":[3,10],"voice":[4],"timbre":[5],"or":[6],"pitch":[7,111],"to":[8,32,47,150],"make":[9],"vocal":[11],"performance":[12,80],"more":[13],"expressive.":[14],"Such":[15],"fluctuations":[16],"are":[17],"called":[18],"singing":[19,24,53,82,134,168],"techniques.":[20,54],"Automatic":[21],"detection":[22],"of":[23,51,75,81,100,132,142,159,167],"techniques":[25],"from":[26],"audio":[27],"tracks":[28],"can":[29,42,61],"be":[30,44,68],"beneficial":[31],"understand":[33],"how":[34],"each":[35,160],"singer":[36],"expresses":[37],"the":[38,48,52,73,76,79,101,122,126,130,139,145,157,165],"performance,":[39],"yet":[40],"it":[41],"also":[43,154],"difficult":[45],"due":[46],"wide":[49],"variety":[50],"A":[55],"deep":[56],"neural":[57],"network":[58],"(DNN)":[59],"model":[60,93,102],"handle":[62],"such":[63],"variety;":[64],"however,":[65],"there":[66],"might":[67],"a":[69,91,95],"possibility":[70],"that":[71,156],"considering":[72],"characteristics":[74],"data":[77],"improves":[78],"technique":[83,135],"detection.":[84],"In":[85,129],"this":[86],"paper,":[87],"we":[88],"propose":[89],"PrimaDNN,":[90],"CRNN":[92],"with":[94],"characteristics-oriented":[96],"improvement.":[97],"The":[98],"features":[99],"are:":[103],"1)":[104],"input":[105],"feature":[106],"representation":[107],"based":[108,120],"on":[109,121,164],"auxiliary":[110],"information":[112],"and":[113,125],"multi-resolution":[114],"mel":[115],"spectrograms,":[116],"2)":[117],"Convolution":[118],"module":[119],"Squeeze-and-excitation":[123],"(SENet)":[124],"Instance":[127],"normalization.":[128],"results":[131,141],"J-POP":[133],"detection,":[136],"PrimaDNN":[137],"achieved":[138],"best":[140],"44.9%":[143],"at":[144],"overall":[146],"macro-F":[147],"measure,":[148],"compared":[149],"conventional":[151],"works.":[152],"We":[153],"found":[155],"contribution":[158],"component":[161],"varies":[162],"depending":[163],"type":[166],"technique.":[169]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
