{"id":"https://openalex.org/W4223988985","doi":"https://doi.org/10.1186/s13636-022-00240-z","title":"Paralinguistic singing attribute recognition using supervised machine learning for describing the classical tenor solo singing voice in vocal pedagogy","display_name":"Paralinguistic singing attribute recognition using supervised machine learning for describing the classical tenor solo singing voice in vocal pedagogy","publication_year":2022,"publication_date":"2022-04-15","ids":{"openalex":"https://openalex.org/W4223988985","doi":"https://doi.org/10.1186/s13636-022-00240-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/35440938"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-022-00240-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00240-z","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-022-00240-z","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-022-00240-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078759643","display_name":"Yanze Xu","orcid":"https://orcid.org/0000-0001-9736-5548"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yanze Xu","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372962","display_name":"Weiqing Wang","orcid":"https://orcid.org/0000-0002-8588-7872"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiqing Wang","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082183177","display_name":"Huahua Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huahua Cui","raw_affiliation_strings":["Advanced Computing East China Sub-Center, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Advanced Computing East China Sub-Center, Suzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051632607","display_name":"Mingyang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingyang Xu","raw_affiliation_strings":["Advanced Computing East China Sub-Center, Suzhou, China"],"affiliations":[{"raw_affiliation_string":"Advanced Computing East China Sub-Center, Suzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Data Science Research Center, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5078759643"],"corresponding_institution_ids":["https://openalex.org/I4210159968"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":1.6375,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82732368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"2022","issue":"1","first_page":"8","last_page":"8"},"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":0.9990000128746033,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983000159263611,"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/paralanguage","display_name":"Paralanguage","score":0.8996055126190186},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7916943430900574},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7483088374137878},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6599211692810059},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6294194459915161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46305251121520996},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4263029396533966},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.13274535536766052},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10945472121238708},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08787405490875244},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.0800519585609436}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.8996055126190186},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7916943430900574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483088374137878},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6599211692810059},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6294194459915161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46305251121520996},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4263029396533966},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.13274535536766052},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10945472121238708},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08787405490875244},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0800519585609436},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13636-022-00240-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00240-z","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-022-00240-z","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmid:35440938","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35440938","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP journal on audio, speech, and music processing","raw_type":null},{"id":"pmh:oai:doaj.org/article:4f5c030cc18c4fb38c60cb78d930e059","is_oa":true,"landing_page_url":"https://doaj.org/article/4f5c030cc18c4fb38c60cb78d930e059","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2022, Iss 1, Pp 1-16 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9011380","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9011380","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP J Audio Speech Music Process","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13636-022-00240-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00240-z","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-022-00240-z","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1062380392","display_name":null,"funder_award_id":"2042021kf003","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1270229601","display_name":null,"funder_award_id":"62171207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3144500776","display_name":null,"funder_award_id":"202007030011","funder_id":"https://openalex.org/F4320335480","funder_display_name":"Guangzhou Municipal Science and Technology Project"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5460491883","display_name":null,"funder_award_id":"201903010040","funder_id":"https://openalex.org/F4320335480","funder_display_name":"Guangzhou Municipal Science and Technology Project"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G727672485","display_name":null,"funder_award_id":"201903010040,202007030011","funder_id":"https://openalex.org/F4320335480","funder_display_name":"Guangzhou Municipal Science and Technology Project"},{"id":"https://openalex.org/G7622982997","display_name":null,"funder_award_id":"2042021kf0039","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8245134708","display_name":null,"funder_award_id":"201903","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8478882202","display_name":null,"funder_award_id":"(2019","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8623956787","display_name":null,"funder_award_id":"90301004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G937128327","display_name":null,"funder_award_id":"201903","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335480","display_name":"Guangzhou Municipal Science and Technology Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4223988985.pdf","grobid_xml":"https://content.openalex.org/works/W4223988985.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W109946471","https://openalex.org/W576379397","https://openalex.org/W786031425","https://openalex.org/W1501669607","https://openalex.org/W1521262965","https://openalex.org/W1570824959","https://openalex.org/W1943497805","https://openalex.org/W1971525508","https://openalex.org/W1995663108","https://openalex.org/W1998038926","https://openalex.org/W2000860788","https://openalex.org/W2002299114","https://openalex.org/W2009955221","https://openalex.org/W2020866611","https://openalex.org/W2028895660","https://openalex.org/W2033012815","https://openalex.org/W2034345148","https://openalex.org/W2037239148","https://openalex.org/W2051580501","https://openalex.org/W2054287732","https://openalex.org/W2058392145","https://openalex.org/W2059970763","https://openalex.org/W2067002903","https://openalex.org/W2074788634","https://openalex.org/W2082927806","https://openalex.org/W2085662862","https://openalex.org/W2089364955","https://openalex.org/W2094085880","https://openalex.org/W2111926505","https://openalex.org/W2115002300","https://openalex.org/W2119417805","https://openalex.org/W2120256304","https://openalex.org/W2128980425","https://openalex.org/W2137371678","https://openalex.org/W2169295472","https://openalex.org/W2170938075","https://openalex.org/W2174219101","https://openalex.org/W2189397211","https://openalex.org/W2194775991","https://openalex.org/W2321391359","https://openalex.org/W2399733683","https://openalex.org/W2405274704","https://openalex.org/W2513507089","https://openalex.org/W2535255545","https://openalex.org/W2612690371","https://openalex.org/W2742451886","https://openalex.org/W2746419079","https://openalex.org/W2889467522","https://openalex.org/W2963351448","https://openalex.org/W2972411915","https://openalex.org/W2973025177","https://openalex.org/W3000819039","https://openalex.org/W3033704032","https://openalex.org/W3037149862","https://openalex.org/W3095513995","https://openalex.org/W3136889378","https://openalex.org/W3213967396","https://openalex.org/W4212774754","https://openalex.org/W4299308749","https://openalex.org/W6828894009","https://openalex.org/W6930575966"],"related_works":["https://openalex.org/W2064370490","https://openalex.org/W3166813893","https://openalex.org/W2910013580","https://openalex.org/W2391900574","https://openalex.org/W3200958703","https://openalex.org/W1990078780","https://openalex.org/W2778981579","https://openalex.org/W2376619307","https://openalex.org/W4250647969","https://openalex.org/W3108667266"],"abstract_inverted_index":{"Humans":[0],"can":[1],"recognize":[2],"someone's":[3],"identity":[4],"through":[5],"their":[6,36],"voice":[7,18,52],"and":[8,29,76,86,103,109,160,197,218,271],"describe":[9,31,49],"the":[10,16,32,50,54,94,126,131,189,193,200,205,211,216,243,247,251,255,258,272,277,282,293,296,300,303,307,319],"timbral":[11,21,33],"phenomena":[12,34],"of":[13,35,58,192,199,257,318],"voices.":[14],"Likewise,":[15],"singing":[17,38,51,66,116,141],"also":[19],"has":[20],"phenomena.":[22],"In":[23,40,184,209,224,242],"vocal":[24,26,55,121],"pedagogy,":[25],"teachers":[27],"listen":[28],"then":[30],"student's":[37],"voice.":[39],"this":[41,71],"study,":[42],"in":[43,97,120,177],"order":[44],"to":[45,48,129,226],"enable":[46],"machines":[47],"from":[53,101,250],"pedagogy":[56,122],"point":[57],"view,":[59],"we":[60,73,143,186,234,245],"perform":[61],"a":[62,232,236],"task":[63],"called":[64],"paralinguistic":[65,115,140,179],"attribute":[67,181],"recognition.":[68],"To":[69],"achieve":[70],"goal,":[72],"first":[74],"construct":[75],"publish":[77],"an":[78,312],"open":[79],"source":[80,107],"dataset":[81],"named":[82],"Singing":[83],"Voice":[84],"Quality":[85],"Technique":[87],"Database":[88],"(SVQTD)":[89],"for":[90,137,231],"supervised":[91,133],"learning.":[92],"All":[93],"audio":[95],"clips":[96],"SVQTD":[98,264],"are":[99,123,170],"downloaded":[100],"YouTube":[102],"processed":[104],"by":[105,285],"music":[106],"separation":[108],"silence":[110],"detection.":[111],"For":[112],"annotation,":[113],"seven":[114],"attributes":[117],"commonly":[118,175],"used":[119],"adopted":[124],"as":[125,204,221,254,287,302],"labels.":[127],"Furthermore,":[128],"explore":[130],"different":[132],"machine":[134,154,166],"learning":[135,158],"algorithm":[136],"classifying":[138],"each":[139],"attribute,":[142],"adopt":[144,235],"three":[145],"main":[146],"frameworks,":[147],"namely":[148],"openSMILE":[149],"features":[150],"with":[151,163,281,311,321],"support":[152,164],"vector":[153,165],"(SF-SVM),":[155],"end-to-end":[156,212],"deep":[157,161],"(E2EDL),":[159],"embedding":[162],"(DE-SVM).":[167],"Our":[168],"methods":[169],"based":[171],"on":[172,263],"existing":[173],"frameworks":[174],"employed":[176],"other":[178],"speech":[180],"recognition":[182],"tasks.":[183],"SF-SVM,":[185],"separately":[187,214],"use":[188,246],"feature":[190,222,304,324],"set":[191],"INTERSPEECH":[194,201],"2009":[195],"Challenge":[196,203],"that":[198,276,298,317],"2016":[202],"SVM":[206,259,279],"classifier's":[207],"input.":[208],"E2EDL,":[210],"framework":[213],"utilizes":[215,299],"ResNet":[217,301],"transformer":[219],"encoder":[220],"extractors.":[223],"particular,":[225],"handle":[227],"two-dimensional":[228],"spectrogram":[229],"input":[230,256,288],"transformer,":[233],"sliced":[237],"multi-head":[238],"self-attention":[239],"(SMSA)":[240],"mechanism.":[241],"DE-SVM,":[244,273],"representation":[248,283],"extracted":[249],"E2EDL":[252,270],"model":[253],"classifier.":[260],"Experimental":[261],"results":[262],"show":[265],"no":[266],"absolute":[267],"winner":[268],"between":[269],"which":[274],"means":[275],"back-end":[278],"classifier":[280],"learned":[284],"E2E":[286],"does":[289],"not":[290],"necessarily":[291],"improve":[292],"performance.":[294],"However,":[295],"DE-SVM":[297],"extractor":[305],"achieves":[306],"best":[308],"average":[309,313],"UAR,":[310],"16%":[314],"improvement":[315],"over":[316],"SF-SVM":[320],"INTERSPEECH's":[322],"hand-crafted":[323],"set.":[325]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}