{"id":"https://openalex.org/W2566935005","doi":"https://doi.org/10.1109/eusipco.2016.7760424","title":"TUT database for acoustic scene classification and sound event detection","display_name":"TUT database for acoustic scene classification and sound event detection","publication_year":2016,"publication_date":"2016-08-01","ids":{"openalex":"https://openalex.org/W2566935005","doi":"https://doi.org/10.1109/eusipco.2016.7760424","mag":"2566935005"},"language":"en","primary_location":{"id":"doi:10.1109/eusipco.2016.7760424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eusipco.2016.7760424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 24th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://www.eurasip.org/Proceedings/Eusipco/Eusipco2016/papers/1570251932.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]},{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I166825849","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"]},{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Toni Heittola","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I166825849","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"]},{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079981416"],"corresponding_institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":55.2244,"has_fulltext":true,"cited_by_count":523,"citation_normalized_percentile":{"value":0.99964884,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1128","last_page":"1132"},"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":0.9984999895095825,"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":0.9825999736785889,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.8273453712463379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7483997344970703},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.6257305145263672},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5928074717521667},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5551401376724243},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5380114912986755},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5304804444313049},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.49317020177841187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47642478346824646},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.41765254735946655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35205578804016113},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.26848113536834717},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19173851609230042}],"concepts":[{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8273453712463379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483997344970703},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.6257305145263672},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5928074717521667},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5551401376724243},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5380114912986755},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5304804444313049},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.49317020177841187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47642478346824646},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.41765254735946655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35205578804016113},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26848113536834717},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19173851609230042},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/eusipco.2016.7760424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eusipco.2016.7760424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 24th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/213360","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/213360","pdf_url":"http://www.eurasip.org/Proceedings/Eusipco/Eusipco2016/papers/1570251932.pdf","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":{"id":"pmh:oai:trepo.tuni.fi:10024/213360","is_oa":true,"landing_page_url":"https://trepo.tuni.fi/handle/10024/213360","pdf_url":"http://www.eurasip.org/Proceedings/Eusipco/Eusipco2016/papers/1570251932.pdf","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"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2566935005.pdf","grobid_xml":"https://content.openalex.org/works/W2566935005.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W172871939","https://openalex.org/W821549425","https://openalex.org/W1568645074","https://openalex.org/W1822987211","https://openalex.org/W2008415856","https://openalex.org/W2021228422","https://openalex.org/W2086384421","https://openalex.org/W2089368853","https://openalex.org/W2092126505","https://openalex.org/W2095147901","https://openalex.org/W2118230268","https://openalex.org/W2123843894","https://openalex.org/W2126109423","https://openalex.org/W2137343183","https://openalex.org/W2144414181","https://openalex.org/W2147917435","https://openalex.org/W2160860215","https://openalex.org/W2173238699","https://openalex.org/W2200864288","https://openalex.org/W2408239454","https://openalex.org/W6683682394"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2766995619","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W4224270619","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2621231815","https://openalex.org/W2048014685","https://openalex.org/W2370972896"],"abstract_inverted_index":{"We":[0],"introduce":[1],"TUT":[2,26,42],"Acoustic":[3],"Scenes":[4],"2016":[5,45],"database":[6,77,106],"for":[7,32,38,113,119],"environmental":[8],"sound":[9,34,39,64],"research,":[10],"consisting":[11],"of":[12,22,47,63,85,121],"binaural":[13],"recordings":[14],"from":[15],"15":[16],"different":[17,122],"acoustic":[18,87],"environments.":[19],"A":[20],"subset":[21],"this":[23,67],"database,":[24],"called":[25],"Sound":[27,43],"Events":[28,44],"2016,":[29],"contains":[30],"annotations":[31],"individual":[33],"events,":[35],"specifically":[36],"created":[37],"event":[40,92],"detection.":[41],"consists":[46],"residential":[48],"area":[49],"and":[50,53,61,73,83,91,101,116],"home":[51],"environments,":[52],"is":[54,107],"manually":[55],"annotated":[56],"to":[57,110],"mark":[58],"onset,":[59],"offset":[60],"label":[62],"events.":[65],"In":[66],"paper":[68],"we":[69],"present":[70],"the":[71,76],"recording":[72],"annotation":[74],"procedure,":[75],"content,":[78],"a":[79],"recommended":[80],"cross-validation":[81],"setup":[82],"performance":[84],"supervised":[86],"scene":[88],"classification":[89],"system":[90,95],"detection":[93],"baseline":[94],"using":[96],"mel":[97],"frequency":[98],"cepstral":[99],"coefficients":[100],"Gaussian":[102],"mixture":[103],"models.":[104],"The":[105],"publicly":[108],"released":[109],"provide":[111],"support":[112],"algorithm":[114],"development":[115],"common":[117],"ground":[118],"comparison":[120],"techniques.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":42},{"year":2022,"cited_by_count":48},{"year":2021,"cited_by_count":62},{"year":2020,"cited_by_count":78},{"year":2019,"cited_by_count":90},{"year":2018,"cited_by_count":74},{"year":2017,"cited_by_count":52},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}