{"id":"https://openalex.org/W2774733779","doi":"https://doi.org/10.1109/waspaa.2017.8169986","title":"Learning vocal mode classifiers from heterogeneous data sources","display_name":"Learning vocal mode classifiers from heterogeneous data sources","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2774733779","doi":"https://doi.org/10.1109/waspaa.2017.8169986","mag":"2774733779"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2017.8169986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8169986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5041823150","display_name":"Zhao Shuyang","orcid":"https://orcid.org/0000-0002-6151-6460"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Zhao Shuyang","raw_affiliation_strings":["Signal Processing Department, Tampere University of Technology, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Signal Processing Department, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059929826","display_name":"Toni Heittola","orcid":"https://orcid.org/0000-0002-8855-0415"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Toni Heittola","raw_affiliation_strings":["Signal Processing Department, Tampere University of Technology, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Signal Processing Department, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Signal Processing Department, Tampere University of Technology, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Signal Processing Department, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041823150"],"corresponding_institution_ids":["https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":0.1866,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49160786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"abs 1605 2688","issue":null,"first_page":"16","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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/normalization","display_name":"Normalization (sociology)","score":0.8344847559928894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7361461520195007},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.698756992816925},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6390247344970703},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6204978823661804},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5582221150398254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5513526797294617},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.46984949707984924}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8344847559928894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7361461520195007},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.698756992816925},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6390247344970703},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6204978823661804},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5582221150398254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5513526797294617},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.46984949707984924},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa.2017.8169986","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8169986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/214042","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/214042","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W149249243","https://openalex.org/W409034240","https://openalex.org/W1524805189","https://openalex.org/W1543335084","https://openalex.org/W1650531274","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2066561607","https://openalex.org/W2070707809","https://openalex.org/W2105885996","https://openalex.org/W2109225367","https://openalex.org/W2124776405","https://openalex.org/W2127825510","https://openalex.org/W2151484683","https://openalex.org/W2171000037","https://openalex.org/W2192412620","https://openalex.org/W2240641835","https://openalex.org/W2296724634","https://openalex.org/W2384495648","https://openalex.org/W2397741330","https://openalex.org/W2676925568","https://openalex.org/W3009927332","https://openalex.org/W3177989406","https://openalex.org/W6614159250","https://openalex.org/W6631241379","https://openalex.org/W6632380265","https://openalex.org/W6636898527","https://openalex.org/W6682194319","https://openalex.org/W6697040288","https://openalex.org/W6712278672","https://openalex.org/W6798679566"],"related_works":["https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W2169074127","https://openalex.org/W83146503","https://openalex.org/W2163707935","https://openalex.org/W202723009","https://openalex.org/W2188612292","https://openalex.org/W4206462905","https://openalex.org/W2165396616","https://openalex.org/W2058882606"],"abstract_inverted_index":{"This":[0],"paper":[1],"targets":[2],"on":[3,12,22,28,65],"a":[4,31],"generalized":[5],"vocal":[6],"mode":[7],"classifier":[8],"(speech/singing)":[9],"that":[10,89,102],"works":[11],"audio":[13],"data":[14,18],"from":[15],"an":[16],"arbitrary":[17],"source.":[19],"Previous":[20],"studies":[21],"sound":[23],"classification":[24,59,91],"are":[25,44],"commonly":[26],"based":[27],"cross-validation":[29,64],"using":[30,63,75,130],"single":[32],"dataset,":[33],"without":[34],"considering":[35],"training-recognition":[36,47,51,122],"mismatch.":[37],"In":[38,53,67],"our":[39],"study,":[40],"two":[41],"experimental":[42,86],"setups":[43],"used:":[45],"matched":[46,55,104],"condition":[48,56,98,105],"and":[49,81],"mismatched":[50,69,97,121],"condition.":[52,123],"the":[54,58,68,71,90,115,118,131],"setup,":[57,70],"performance":[60,72,116,126],"is":[61,73,93],"evaluated":[62,74],"TUT-vocal-2016.":[66],"seven":[76],"other":[77],"datasets":[78],"for":[79,83],"training":[80],"TUT-vocal-2016":[82],"testing.":[84],"The":[85,124],"results":[87],"demonstrate":[88],"accuracy":[92],"much":[94],"lower":[95],"in":[96,103,117],"(69.6%),":[99],"compared":[100],"to":[101,113],"(95.5%).":[106],"Various":[107],"feature":[108],"normalization":[109],"methods":[110],"were":[111],"tested":[112],"improve":[114],"setup":[119],"of":[120],"best":[125],"(96.8%)":[127],"was":[128],"obtained":[129],"proposed":[132],"subdataset-wise":[133],"normalization.":[134]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}