{"id":"https://openalex.org/W2773284573","doi":"https://doi.org/10.1109/waspaa.2017.8170047","title":"Assessment of human and machine performance in acoustic scene classification: Dcase 2016 case study","display_name":"Assessment of human and machine performance in acoustic scene classification: Dcase 2016 case study","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2773284573","doi":"https://doi.org/10.1109/waspaa.2017.8170047","mag":"2773284573"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2017.8170047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8170047","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/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Department of Signal Processing, Korkeakoulunkatu 10, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Korkeakoulunkatu 10, Tampere, Finland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059929826","display_name":"Toni Heittola","orcid":"https://orcid.org/0000-0002-8855-0415"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toni Heittola","raw_affiliation_strings":["Department of Signal Processing, Korkeakoulunkatu 10, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Korkeakoulunkatu 10, Tampere, Finland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Department of Signal Processing, Korkeakoulunkatu 10, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Korkeakoulunkatu 10, Tampere, Finland","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079981416"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9332,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.77029527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"319","last_page":"323"},"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":0.9990000128746033,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9940999746322632,"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/computer-science","display_name":"Computer science","score":0.6936421990394592},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.6753160357475281},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6328431963920593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.582929790019989},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5735102295875549},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4598146378993988},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4194732904434204},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36457163095474243},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15164265036582947},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06115838885307312},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.05389183759689331}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6936421990394592},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.6753160357475281},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6328431963920593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.582929790019989},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5735102295875549},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4598146378993988},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4194732904434204},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36457163095474243},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15164265036582947},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06115838885307312},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.05389183759689331},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa.2017.8170047","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8170047","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:10024/214020","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/214020","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":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W34415881","https://openalex.org/W1496437685","https://openalex.org/W2084413241","https://openalex.org/W2086384421","https://openalex.org/W2095147901","https://openalex.org/W2103235956","https://openalex.org/W2137343183","https://openalex.org/W2477915622","https://openalex.org/W2566935005","https://openalex.org/W2775505379","https://openalex.org/W3092213245","https://openalex.org/W3103385400","https://openalex.org/W6601414320","https://openalex.org/W6721490382","https://openalex.org/W6747331233","https://openalex.org/W6784489076","https://openalex.org/W6980901144","https://openalex.org/W7023426766"],"related_works":["https://openalex.org/W2475724061","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642","https://openalex.org/W2366328218","https://openalex.org/W2509366663"],"abstract_inverted_index":{"Human":[0],"and":[1,37,42],"machine":[2,21,59],"performance":[3,74],"in":[4,73,103],"acoustic":[5,106],"scene":[6],"classification":[7],"is":[8,24],"examined":[9],"through":[10,48],"a":[11,49],"parallel":[12],"experiment":[13],"using":[14],"TUT":[15],"Acoustic":[16,40],"Scenes":[17,41],"2016":[18,33],"dataset.":[19],"The":[20,44],"learning":[22],"perspective":[23],"presented":[25],"based":[26],"on":[27,35],"the":[28,32,67,84,90],"systems":[29],"submitted":[30,93],"for":[31,83],"challenge":[34],"Detection":[36],"Classification":[38],"of":[39,77,92,100],"Events.":[43],"human":[45,101],"performance,":[46],"assessed":[47],"listening":[50],"experiment,":[51,68],"was":[52],"found":[53],"to":[54,70,89,97],"be":[55],"significantly":[56],"lower":[57],"than":[58],"performance.":[60],"Test":[61],"subjects":[62],"exhibited":[63],"different":[64],"behavior":[65],"throughout":[66],"leading":[69],"significant":[71],"differences":[72],"between":[75],"groups":[76],"subjects.":[78],"An":[79],"expert":[80],"listener":[81],"trained":[82],"task":[85],"obtained":[86],"similar":[87],"accuracy":[88],"average":[91],"systems,":[94],"comparable":[95],"also":[96],"previous":[98],"studies":[99],"abilities":[102],"recognizing":[104],"everyday":[105],"scenes.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}