{"id":"https://openalex.org/W2034215399","doi":"https://doi.org/10.1109/icassp.2013.6639360","title":"Supervised model training for overlapping sound events based on unsupervised source separation","display_name":"Supervised model training for overlapping sound events based on unsupervised source separation","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2034215399","doi":"https://doi.org/10.1109/icassp.2013.6639360","mag":"2034215399"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5059929826","display_name":"Toni Heittola","orcid":"https://orcid.org/0000-0002-8855-0415"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"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/I150589677","display_name":"Tampere University of Applied Sciences","ror":"https://ror.org/00bwtjf83","country_code":"FI","type":"education","lineage":["https://openalex.org/I150589677"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Toni Heittola","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Finland","Dept. of Signal Process., Tampere Univ. of Technol., Tampere, , Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Dept. of Signal Process., Tampere Univ. of Technol., Tampere, , Finland","institution_ids":["https://openalex.org/I150589677"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079981416","display_name":"Annamaria Mesaros","orcid":"https://orcid.org/0000-0002-6640-9752"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Department of Information and Computer Science, Aalto University, Finland","Department of Information and Computer Science, Aalto University, Espoo, Finland#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Information and Computer Science, Aalto University, Espoo, Finland#TAB#","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I150589677","display_name":"Tampere University of Applied Sciences","ror":"https://ror.org/00bwtjf83","country_code":"FI","type":"education","lineage":["https://openalex.org/I150589677"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Finland","Dept. of Signal Process., Tampere Univ. of Technol., Tampere, , Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Dept. of Signal Process., Tampere Univ. of Technol., Tampere, , Finland","institution_ids":["https://openalex.org/I150589677"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007583477","display_name":"Moncef Gabbouj","orcid":"https://orcid.org/0000-0002-9788-2323"},"institutions":[{"id":"https://openalex.org/I150589677","display_name":"Tampere University of Applied Sciences","ror":"https://ror.org/00bwtjf83","country_code":"FI","type":"education","lineage":["https://openalex.org/I150589677"]},{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"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":"Moncef Gabbouj","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology, Finland","Dept. of Signal Process., Tampere Univ. of Technol., Tampere, , Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Dept. of Signal Process., Tampere Univ. of Technol., Tampere, , Finland","institution_ids":["https://openalex.org/I150589677"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059929826"],"corresponding_institution_ids":["https://openalex.org/I150589677","https://openalex.org/I166825849","https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":3.2156,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.92251369,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8677","last_page":"8681"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9936000108718872,"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/computer-science","display_name":"Computer science","score":0.8021407127380371},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7125817537307739},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7116132974624634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5724214315414429},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5368462204933167},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5123249292373657},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4612613320350647},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.45159173011779785},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.44203686714172363},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42953428626060486},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41450533270835876},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.0993032455444336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021407127380371},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7125817537307739},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7116132974624634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5724214315414429},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5368462204933167},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5123249292373657},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4612613320350647},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.45159173011779785},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.44203686714172363},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42953428626060486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41450533270835876},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0993032455444336},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639360","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639360","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.390.5447","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.390.5447","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tut.fi/~moncef/publications/supervised-model-ICASSP-2013.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W84880661","https://openalex.org/W1533561824","https://openalex.org/W1822987211","https://openalex.org/W2021096090","https://openalex.org/W2049633694","https://openalex.org/W2074764925","https://openalex.org/W2086468861","https://openalex.org/W2089368853","https://openalex.org/W2114777924","https://openalex.org/W2115447976","https://openalex.org/W2123843894","https://openalex.org/W2126109423","https://openalex.org/W2130640900","https://openalex.org/W2141739745","https://openalex.org/W2150415460","https://openalex.org/W2160860215","https://openalex.org/W2165320399","https://openalex.org/W2327970305","https://openalex.org/W2331166300","https://openalex.org/W6603374476","https://openalex.org/W6632323398","https://openalex.org/W6677170001","https://openalex.org/W6684354967","https://openalex.org/W6702387769","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2863202953","https://openalex.org/W2049866946"],"abstract_inverted_index":{"Sound":[0],"event":[1],"detection":[2,130],"is":[3,17,40],"addressed":[4],"in":[5,34,128],"the":[6,25,48,63,69,76,86,91,106,129],"presence":[7],"of":[8,27,124],"overlapping":[9,28],"sounds.":[10],"Unsupervised":[11],"sound":[12,50],"source":[13],"separation":[14],"into":[15],"streams":[16,89],"used":[18],"as":[19],"a":[20,32,98,121],"preprocessing":[21],"step":[22],"to":[23,61,67,119],"minimize":[24],"interference":[26],"events.":[29],"This":[30],"poses":[31],"problem":[33],"supervised":[35],"model":[36],"training,":[37],"since":[38],"there":[39],"no":[41],"knowledge":[42],"about":[43],"which":[44],"separated":[45],"stream":[46,66,79,112],"contains":[47],"targeted":[49],"source.":[51],"We":[52],"propose":[53],"two":[54],"iterative":[55],"approaches":[56,94,116],"based":[57],"on":[58],"EM":[59],"algorithm":[60],"select":[62],"most":[64,77,87],"likely":[65,78],"contain":[68],"target":[70],"sound:":[71],"one":[72,82],"by":[73,83],"selecting":[74],"always":[75],"and":[80],"another":[81],"gradually":[84],"eliminating":[85],"unlikely":[88],"from":[90,102],"training.":[92],"The":[93],"were":[95,117],"evaluated":[96],"with":[97],"database":[99],"containing":[100],"recordings":[101],"various":[103],"contexts,":[104],"against":[105],"baseline":[107],"system":[108],"trained":[109],"without":[110],"applying":[111],"selection.":[113],"Both":[114],"proposed":[115],"found":[118],"give":[120],"reasonable":[122],"increase":[123],"8":[125],"percentage":[126],"units":[127],"accuracy.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}