{"id":"https://openalex.org/W3117812988","doi":"https://doi.org/10.1145/3395035.3425252","title":"The Influence of Blind Source Separation on Mixed Audio Speech and Music Emotion Recognition","display_name":"The Influence of Blind Source Separation on Mixed Audio Speech and Music Emotion Recognition","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3117812988","doi":"https://doi.org/10.1145/3395035.3425252","mag":"3117812988"},"language":"en","primary_location":{"id":"doi:10.1145/3395035.3425252","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3395035.3425252","pdf_url":null,"source":{"id":"https://openalex.org/S4306506653","display_name":"Companion Publication of the 2020 International Conference on Multimodal Interaction","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},"type":"conference-paper","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/A5021623854","display_name":"Casper Laugs","orcid":null},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Casper Laugs","raw_affiliation_strings":["Utrecht University, Utrecht, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Utrecht University, Utrecht, Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089308804","display_name":"Hendrik Vincent Koops","orcid":"https://orcid.org/0000-0002-6980-7027"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hendrik Vincent Koops","raw_affiliation_strings":["RTL The Netherlands, Hilversum, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RTL The Netherlands, Hilversum, Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071940615","display_name":"Daan Odijk","orcid":"https://orcid.org/0000-0003-0369-8857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daan Odijk","raw_affiliation_strings":["RTL The Netherlands, Hilversum, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RTL The Netherlands, Hilversum, Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050585145","display_name":"Heysem Kaya","orcid":"https://orcid.org/0000-0001-7947-5508"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Heysem Kaya","raw_affiliation_strings":["Utrecht University, Utrecht, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Utrecht University, Utrecht, Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041358150","display_name":"Anja Volk","orcid":"https://orcid.org/0000-0002-6755-9592"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Anja Volk","raw_affiliation_strings":["Utrecht University, Utrecht, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Utrecht University, Utrecht, Netherlands","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4922,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.62191822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"71"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991999864578247,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7486851215362549},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.696399450302124},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5286581516265869},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.4514155387878418},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.436295747756958},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.40429314970970154},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34949958324432373},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2965076267719269}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7486851215362549},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.696399450302124},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5286581516265869},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.4514155387878418},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.436295747756958},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.40429314970970154},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34949958324432373},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2965076267719269}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3395035.3425252","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3395035.3425252","pdf_url":null,"source":{"id":"https://openalex.org/S4306506653","display_name":"Companion Publication of the 2020 International Conference on Multimodal Interaction","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2020 International Conference on Multimodal Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.library.uu.nl:1874/415586","is_oa":false,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/415586","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"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":"Contribution to conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W189934255","https://openalex.org/W1777859530","https://openalex.org/W1992855217","https://openalex.org/W2011853905","https://openalex.org/W2032018075","https://openalex.org/W2066776249","https://openalex.org/W2074788634","https://openalex.org/W2082927806","https://openalex.org/W2085662862","https://openalex.org/W2087407704","https://openalex.org/W2089705003","https://openalex.org/W2149628368","https://openalex.org/W2171848217","https://openalex.org/W2292850616","https://openalex.org/W2399733683","https://openalex.org/W2501385940","https://openalex.org/W2592535880","https://openalex.org/W2600087639","https://openalex.org/W2739665188","https://openalex.org/W2759261664","https://openalex.org/W2803193013","https://openalex.org/W2889107526","https://openalex.org/W2911964244","https://openalex.org/W2964370293","https://openalex.org/W2969889150","https://openalex.org/W2990387939","https://openalex.org/W2997399314","https://openalex.org/W2997591727","https://openalex.org/W3021076218"],"related_works":["https://openalex.org/W2157598242","https://openalex.org/W2131711534","https://openalex.org/W3159882232","https://openalex.org/W2620660273","https://openalex.org/W2122924390","https://openalex.org/W642007152","https://openalex.org/W2042419400","https://openalex.org/W2403025337","https://openalex.org/W1853164203","https://openalex.org/W4385474305"],"abstract_inverted_index":{"While":[0],"both":[1,30,63],"speech":[2,31,64,186],"emotion":[3,7,23,67,152,180],"recognition":[4,8,21,68,153],"and":[5,32,65,73,78,169,187],"music":[6,33,66,188],"have":[9],"been":[10],"studied":[11],"extensively":[12],"in":[13],"different":[14],"communities,":[15],"little":[16],"research":[17],"went":[18],"into":[19],"the":[20,85,105],"of":[22,84],"from":[24,48,181],"mixed":[25,49,60,86,94,125,138,156],"audio":[26,50,61,95,116,146,157],"sources,":[27,51],"i.e.":[28],"when":[29,134],"are":[34,43,176,190],"present.":[35],"However,":[36],"many":[37],"application":[38],"scenarios":[39],"require":[40],"models":[41,111,154],"that":[42,109],"able":[44,118],"to":[45,119],"extract":[46],"emotions":[47],"such":[52],"as":[53],"television":[54],"content.":[55],"This":[56],"paper":[57],"studies":[58],"how":[59],"affects":[62],"using":[69],"a":[70,93],"random":[71],"forest":[72],"deep":[74],"neural":[75],"network":[76],"model,":[77],"investigates":[79],"if":[80],"blind":[81,147,171],"source":[82,148,172],"separation":[83],"signal":[87],"beforehand":[88],"is":[89],"beneficial.":[90],"We":[91,107],"created":[92],"dataset,":[96],"with":[97,145,168],"25%":[98],"speech-music":[99],"overlap":[100],"without":[101,170],"contextual":[102],"relationship":[103],"between":[104],"two.":[106],"show":[108],"specialized":[110],"for":[112,178],"speech-only":[113],"or":[114,161],"music-only":[115,166],"were":[117],"achieve":[120,158],"merely":[121],"'chance-level'":[122],"performance":[123,131,142,159,164],"on":[124,136,155,165],"audio.":[126],"For":[127],"speech,":[128],"above":[129],"chance-level":[130],"was":[132,143],"achieved":[133,144],"trained":[135],"raw":[137],"audio,":[139,167],"but":[140],"optimal":[141],"separated":[149],"beforehand.":[150],"Music":[151],"approaching":[160],"even":[162],"surpassing":[163],"separation.":[173],"Our":[174],"results":[175],"important":[177],"estimating":[179],"real-world":[182],"data,":[183],"where":[184],"individual":[185],"tracks":[189],"often":[191],"not":[192],"available.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}
