{"id":"https://openalex.org/W3189795983","doi":"https://doi.org/10.23919/eusipco54536.2021.9615984","title":"Robust Acoustic Scene Classification in the Presence of Active Foreground Speech","display_name":"Robust Acoustic Scene Classification in the Presence of Active Foreground Speech","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3189795983","doi":"https://doi.org/10.23919/eusipco54536.2021.9615984","mag":"3189795983"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9615984","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9615984","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/8721207/file/8721210.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101709678","display_name":"Siyuan Song","orcid":"https://orcid.org/0009-0009-3103-686X"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Siyuan Song","raw_affiliation_strings":["Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032699386","display_name":"Brecht Desplanques","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Brecht Desplanques","raw_affiliation_strings":["Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083836827","display_name":"Celest De Moor","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Celest De Moor","raw_affiliation_strings":["Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046536366","display_name":"Kris Demuynck","orcid":"https://orcid.org/0000-0001-8525-7160"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kris Demuynck","raw_affiliation_strings":["Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nilesh Madhu","raw_affiliation_strings":["Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, IDLab, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101709678"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":0.5166,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63703704,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"995","last_page":"999"},"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":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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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":0.7862721681594849},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6669076681137085},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6429116725921631},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6398494243621826},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5222340822219849},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5105148553848267},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4973640739917755},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4813895523548126},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4741848409175873},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4583629071712494},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4237109124660492},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4236454665660858},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.4164814054965973},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41222047805786133},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.28516584634780884},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2151055932044983},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12674272060394287}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7862721681594849},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6669076681137085},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6429116725921631},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6398494243621826},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5222340822219849},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5105148553848267},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4973640739917755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4813895523548126},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4741848409175873},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4583629071712494},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4237109124660492},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4236454665660858},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.4164814054965973},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41222047805786133},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28516584634780884},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2151055932044983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12674272060394287},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9615984","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9615984","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:8721207","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/8721207","pdf_url":"https://biblio.ugent.be/publication/8721207/file/8721210.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9789082797060","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:8721207","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/8721207","pdf_url":"https://biblio.ugent.be/publication/8721207/file/8721210.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9789082797060","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5199999809265137,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3189795983.pdf","grobid_xml":"https://content.openalex.org/works/W3189795983.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2051428568","https://openalex.org/W2053023379","https://openalex.org/W2086384421","https://openalex.org/W2103235956","https://openalex.org/W2146194791","https://openalex.org/W2146635662","https://openalex.org/W2150769028","https://openalex.org/W2155998647","https://openalex.org/W2158336491","https://openalex.org/W2403891086","https://openalex.org/W2507424718","https://openalex.org/W2566935005","https://openalex.org/W2775794021","https://openalex.org/W2799415746","https://openalex.org/W2900315145","https://openalex.org/W2969024962","https://openalex.org/W3042317849","https://openalex.org/W3095510156","https://openalex.org/W3111611403","https://openalex.org/W6780496662"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W2048014685","https://openalex.org/W4385672897","https://openalex.org/W2370972896","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948"],"abstract_inverted_index":{"We":[0,113],"present":[1],"an":[2,92],"iVector":[3,33,81],"based":[4,157],"Acoustic":[5],"Scene":[6],"Classification":[7],"(ASC)":[8],"system":[9],"suited":[10],"for":[11,109],"real":[12],"life":[13],"settings":[14],"where":[15],"active":[16],"foreground":[17,69,128],"speech":[18,129],"can":[19,102,184],"be":[20,103],"present.":[21],"In":[22],"the":[23,36,53,63,72,77,80,95,116,137,147,155,177,187],"proposed":[24],"system,":[25],"each":[26],"recording":[27],"is":[28,49,121,130],"represented":[29],"by":[30],"a":[31,68,106],"fixed-length":[32],"that":[34,88,115,154],"models":[35,48],"recording's":[37],"important":[38],"properties.":[39],"A":[40],"regularized":[41],"Gaussian":[42],"backend":[43],"classifier":[44],"with":[45],"class-specific":[46],"covariance":[47],"used":[50],"to":[51,123,132,135,169],"extract":[52],"relevant":[54],"acoustic":[55],"scene":[56],"information":[57],"from":[58,91],"these":[59],"iVectors.":[60],"To":[61],"alleviate":[62],"large":[64],"performance":[65],"degradation":[66],"when":[67],"speaker":[70],"dominates":[71],"captured":[73],"signal,":[74],"we":[75],"investigate":[76],"use":[78,117],"of":[79,94,118,167,189],"framework":[82],"on":[83,146],"Mel-Frequency":[84],"Cepstral":[85],"Coefficients":[86],"(MFCCs)":[87],"are":[89],"derived":[90],"estimate":[93],"noise":[96],"power":[97],"spectral":[98],"density.":[99],"This":[100],"noise-floor":[101,119,156],"extracted":[104],"in":[105,126,176,191],"statistical":[107],"manner":[108],"single":[110],"channel":[111],"recordings.":[112],"show":[114,153],"features":[120,158],"complementary":[122],"multi-condition":[124,160],"training":[125,133,140,161],"which":[127],"added":[131],"signal":[134],"reduce":[136],"mismatch":[138],"between":[139],"and":[141,159],"testing":[142],"conditions.":[143,180],"Experimental":[144],"results":[145,183],"DCASE":[148],"2016":[149],"Task":[150],"1":[151],"dataset":[152],"realize":[162],"significant":[163],"classification":[164],"accuracy":[165],"gains":[166],"up":[168],"more":[170],"than":[171],"25":[172],"percentage":[173],"points":[174],"(absolute)":[175],"most":[178],"adverse":[179],"These":[181],"promising":[182],"further":[185],"facilitate":[186],"integration":[188],"ASC":[190],"resource-constrained":[192],"devices":[193],"such":[194],"as":[195],"hearables.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-04T08:04:53.788161","created_date":"2025-10-10T00:00:00"}