{"id":"https://openalex.org/W4402437854","doi":"https://doi.org/10.1145/3678299.3678326","title":"Rebetiko Singer Identification: Fine-tuning and explaining deep pretrained transformer models","display_name":"Rebetiko Singer Identification: Fine-tuning and explaining deep pretrained transformer models","publication_year":2024,"publication_date":"2024-09-11","ids":{"openalex":"https://openalex.org/W4402437854","doi":"https://doi.org/10.1145/3678299.3678326"},"language":"en","primary_location":{"id":"doi:10.1145/3678299.3678326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3678299.3678326","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Audio Mostly 2024 - Explorations in Sonic Cultures","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3678299.3678326","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001450313","display_name":"\u039c\u03ac\u03be\u03b9\u03bc\u03bf\u03c2 \u039a\u03b1\u03bb\u03b9\u03b1\u03ba\u03ac\u03c4\u03c3\u03bf\u03c2-\u03a0\u03b1\u03c0\u03b1\u03ba\u03ce\u03c3\u03c4\u03b1\u03c2","orcid":"https://orcid.org/0000-0002-9062-9915"},"institutions":[{"id":"https://openalex.org/I26840924","display_name":"Mediterranean University","ror":"https://ror.org/03tsjvt68","country_code":"ME","type":"education","lineage":["https://openalex.org/I26840924"]},{"id":"https://openalex.org/I28710699","display_name":"Hellenic Mediterranean University","ror":"https://ror.org/039ce0m20","country_code":"GR","type":"education","lineage":["https://openalex.org/I28710699"]}],"countries":["GR","ME"],"is_corresponding":true,"raw_author_name":"Maximos Kaliakatsos-Papakostas","raw_affiliation_strings":["Department of Music Technology and Acoustics, Hellenic Mediterranean University, GR"],"raw_orcid":"https://orcid.org/0000-0002-9062-9915","affiliations":[{"raw_affiliation_string":"Department of Music Technology and Acoustics, Hellenic Mediterranean University, GR","institution_ids":["https://openalex.org/I26840924","https://openalex.org/I28710699"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051900966","display_name":"Asterios Zacharakis","orcid":"https://orcid.org/0000-0003-2024-6924"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Asteris Zacharakis","raw_affiliation_strings":["School of Music Studies, Aristotle University of Thessaloniki, Greece"],"raw_orcid":"https://orcid.org/0000-0003-2024-6924","affiliations":[{"raw_affiliation_string":"School of Music Studies, Aristotle University of Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035270826","display_name":"Konstantinos Velenis","orcid":"https://orcid.org/0009-0006-7299-4763"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos Velenis","raw_affiliation_strings":["School of Music Studies, Aristotle University of Thessaloniki, GR"],"raw_orcid":"https://orcid.org/0009-0006-7299-4763","affiliations":[{"raw_affiliation_string":"School of Music Studies, Aristotle University of Thessaloniki, GR","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073323305","display_name":"Emilios Cambouropoulos","orcid":"https://orcid.org/0000-0002-6887-4287"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Emilios Cambouropoulos","raw_affiliation_strings":["School of Music Studies, School of Music Studies, Aristotle University of Thessaloniki, Greece, Greece"],"raw_orcid":"https://orcid.org/0000-0002-6887-4287","affiliations":[{"raw_affiliation_string":"School of Music Studies, School of Music Studies, Aristotle University of Thessaloniki, Greece, Greece","institution_ids":["https://openalex.org/I21370196"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5001450313"],"corresponding_institution_ids":["https://openalex.org/I26840924","https://openalex.org/I28710699"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12395746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"285","last_page":"291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11052","display_name":"Energy Load and Power Forecasting","score":0.9646000266075134,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11052","display_name":"Energy Load and Power Forecasting","score":0.9646000266075134,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9605000019073486,"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/T12169","display_name":"Non-Destructive Testing Techniques","score":0.944599986076355,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7291251420974731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6559786796569824},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.524931013584137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44435402750968933},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43177956342697144},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2029135525226593},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.18226996064186096},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.13414448499679565}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7291251420974731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6559786796569824},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.524931013584137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44435402750968933},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43177956342697144},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2029135525226593},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.18226996064186096},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.13414448499679565},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3678299.3678326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3678299.3678326","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Audio Mostly 2024 - Explorations in Sonic Cultures","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3678299.3678326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3678299.3678326","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Audio Mostly 2024 - Explorations in Sonic Cultures","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1607493952","https://openalex.org/W1986595194","https://openalex.org/W2005383150","https://openalex.org/W2056148068","https://openalex.org/W2339865014","https://openalex.org/W2543693073","https://openalex.org/W2587767513","https://openalex.org/W2901278670","https://openalex.org/W2905472553","https://openalex.org/W2981731882","https://openalex.org/W3093033010","https://openalex.org/W3116286104","https://openalex.org/W3203140070","https://openalex.org/W3209059054","https://openalex.org/W4372260250","https://openalex.org/W4384112157"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"In":[0],"Rebetiko":[1,96,166,184],"music,":[2],"the":[3,16,32,83,143,150,161,179],"distinctive":[4],"vocal":[5],"qualities":[6],"of":[7,18,89,163,183],"individual":[8],"singers,":[9,12],"especially":[10],"renowned":[11],"are":[13,59,154],"often":[14],"at":[15],"centre":[17],"attention,":[19],"as":[20],"their":[21,69,71],"unique":[22],"timbre":[23],"and":[24,85,111,131,181],"ornamentations":[25],"play":[26],"a":[27,44],"crucial":[28,175],"role":[29],"in":[30],"defining":[31],"genre\u2019s":[33],"characteristics.":[34],"Pre-trained":[35],"deep":[36],"learning":[37,152],"models":[38,58,92],"on":[39],"human":[40],"voice":[41,91,100],"data":[42],"offer":[43],"good":[45],"starting":[46],"point":[47],"for":[48,68,87,94,165,176],"fine-tuning":[49,164],"to":[50],"classify":[51],"small-sized":[52],"voice-related":[53],"datasets.":[54],"While":[55],"these":[56],"fine-tuned":[57,93],"\"black":[60,144],"boxes\"":[61],"that":[62],"do":[63],"not":[64,158],"provide":[65],"direct":[66],"explanations":[67],"classifications,":[70],"internal":[72],"latent":[73],"representations":[74],"can":[75,115],"be":[76,116],"explored":[77],"through":[78,119],"visualizations.":[79],"This":[80,156],"study":[81,157],"analyzes":[82],"performance":[84],"possibilities":[86],"explainability":[88],"pre-trained":[90],"identifying":[95],"singers":[97,107],"using":[98],"separated":[99],"signals":[101],"from":[102,142],"original":[103],"recordings.":[104],"The":[105],"selected":[106],"exhibit":[108],"diverse":[109],"timbral":[110],"delivery":[112],"styles,":[113],"which":[114,173],"numerically":[117],"represented":[118],"perceptually":[120],"relevant":[121],"audio":[122,138],"features":[123,139],"(e.g.,":[124],"fundamental":[125],"frequency,":[126],"spectral":[127],"centroid,":[128],"vibrato":[129],"rate":[130],"depth,":[132],"inharmonicity,":[133],"etc.).":[134],"By":[135],"comparing":[136],"extracted":[137],"with":[140],"visualizations":[141],"box\"":[145],"model,":[146],"valuable":[147],"insights":[148],"into":[149],"model\u2019s":[151],"process":[153],"gained.":[155],"only":[159],"demonstrates":[160],"effectiveness":[162],"singer":[167],"identification":[168],"but":[169],"also":[170],"enhances":[171],"explainability,":[172],"is":[174],"better":[177],"understanding":[178],"characteristics":[180],"trends":[182],"singing.":[185]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
