{"id":"https://openalex.org/W1511170870","doi":"https://doi.org/10.1109/icassp.2015.7177950","title":"Sound event detection in real life recordings using coupled matrix factorization of spectral representations and class activity annotations","display_name":"Sound event detection in real life recordings using coupled matrix factorization of spectral representations and class activity annotations","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1511170870","doi":"https://doi.org/10.1109/icassp.2015.7177950","mag":"1511170870"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7177950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7177950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":[{"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/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["FI","US"],"is_corresponding":true,"raw_author_name":"Annamaria Mesaros","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology","Department of Signal Processing Tampere University of Technology, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210121626","https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Department of Signal Processing Tampere University of Technology, 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"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Toni Heittola","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology","Department of Signal Processing Tampere University of Technology, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210121626","https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Department of Signal Processing Tampere University of Technology, Finland","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028197135","display_name":"Onur Dikmen","orcid":"https://orcid.org/0000-0002-6565-4860"},"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":"Onur Dikmen","raw_affiliation_strings":["Department of Information and Computer Science, Aalto University","[Department of Information and Computer Science, Aalto University, Finland]"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, Aalto University","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"[Department of Information and Computer Science, Aalto University, Finland]","institution_ids":["https://openalex.org/I9927081"]}]},{"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/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/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Department of Signal Processing, Tampere University of Technology","Department of Signal Processing Tampere University of Technology, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing, Tampere University of Technology","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210121626","https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Department of Signal Processing Tampere University of Technology, Finland","institution_ids":["https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079981416"],"corresponding_institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210121626","https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":11.8859,"has_fulltext":false,"cited_by_count":100,"citation_normalized_percentile":{"value":0.99001616,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"155"},"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":0.9998999834060669,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9979000091552734,"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/matrix-decomposition","display_name":"Matrix decomposition","score":0.8421676158905029},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7386622428894043},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.7116827964782715},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6507545113563538},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6006907820701599},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.5594877004623413},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5195303559303284},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5023782253265381},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5015406608581543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4762282967567444},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4702034592628479},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4459611773490906},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.42109841108322144},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1538386046886444},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.09674504399299622}],"concepts":[{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.8421676158905029},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7386622428894043},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7116827964782715},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6507545113563538},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6006907820701599},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.5594877004623413},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5195303559303284},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5023782253265381},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5015406608581543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4762282967567444},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4702034592628479},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4459611773490906},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.42109841108322144},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1538386046886444},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.09674504399299622},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"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":2,"locations":[{"id":"doi:10.1109/icassp.2015.7177950","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7177950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/212861","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/212861","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1512460134","https://openalex.org/W1533561824","https://openalex.org/W1902027874","https://openalex.org/W2008415856","https://openalex.org/W2034215399","https://openalex.org/W2034424181","https://openalex.org/W2074764925","https://openalex.org/W2077159900","https://openalex.org/W2089368853","https://openalex.org/W2090200552","https://openalex.org/W2114508388","https://openalex.org/W2116681922","https://openalex.org/W2123843894","https://openalex.org/W2126109423","https://openalex.org/W2130295778","https://openalex.org/W2144421983","https://openalex.org/W2160860215","https://openalex.org/W2165320399","https://openalex.org/W2171680721","https://openalex.org/W2404400936","https://openalex.org/W2561557072","https://openalex.org/W4233392025","https://openalex.org/W6630793456","https://openalex.org/W6632323398","https://openalex.org/W6684354967","https://openalex.org/W6685224139"],"related_works":["https://openalex.org/W2133030781","https://openalex.org/W2037504162","https://openalex.org/W1964120219","https://openalex.org/W1525739182","https://openalex.org/W2124890708","https://openalex.org/W2382728211","https://openalex.org/W2375896765","https://openalex.org/W2097588749","https://openalex.org/W2549837900","https://openalex.org/W1511170870"],"abstract_inverted_index":{"Methods":[0],"for":[1,88],"detection":[2],"of":[3,29,56,81,92,102],"overlapping":[4],"sound":[5],"events":[6],"in":[7,41],"audio":[8,58],"involve":[9],"matrix":[10,44],"factorization":[11,45],"approaches,":[12],"often":[13],"assigning":[14],"separated":[15],"components":[16,36],"to":[17,70],"event":[18],"classes.":[19],"We":[20],"present":[21],"a":[22,38,42,100],"method":[23,33],"that":[24],"bypasses":[25],"the":[26,35,48,52,57,61,66,73,90,93],"supervised":[27],"construction":[28],"class":[30,53,74],"models.":[31],"The":[32,95],"learns":[34],"as":[37],"non-negative":[39],"dictionary":[40],"coupled":[43],"problem,":[46],"where":[47],"spectral":[49],"representation":[50],"and":[51,106],"activity":[54],"annotation":[55],"signal":[59],"share":[60],"activation":[62],"matrix.":[63],"In":[64],"testing,":[65],"dictionaries":[67],"are":[68,86],"used":[69],"estimate":[71],"directly":[72],"activations.":[75],"For":[76],"dealing":[77],"with":[78],"large":[79],"amount":[80],"training":[82],"data,":[83],"two":[84],"methods":[85,96],"proposed":[87],"reducing":[89],"size":[91],"dictionary.":[94],"were":[97],"tested":[98],"on":[99],"database":[101],"real":[103],"life":[104],"recordings,":[105],"outperformed":[107],"previous":[108],"approaches":[109],"by":[110],"over":[111],"10%.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":25},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
