{"id":"https://openalex.org/W4403511706","doi":"https://doi.org/10.23919/spa61993.2024.10715626","title":"Salient sound extraction using deep neural networks predicting complex masks","display_name":"Salient sound extraction using deep neural networks predicting complex masks","publication_year":2024,"publication_date":"2024-09-25","ids":{"openalex":"https://openalex.org/W4403511706","doi":"https://doi.org/10.23919/spa61993.2024.10715626"},"language":"en","primary_location":{"id":"doi:10.23919/spa61993.2024.10715626","is_oa":false,"landing_page_url":"https://doi.org/10.23919/spa61993.2024.10715626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01JXZEJR91STGTAWXK0JV8649J/file/01JXZETQ2F1M8NPF7KW7CR6NAX.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045397888","display_name":"Tomasz Grzywalski","orcid":"https://orcid.org/0000-0002-9388-0494"},"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":"Tomasz Grzywalski","raw_affiliation_strings":["Ghent University,Department of Information Technology,Ghent,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University,Department of Information Technology,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069519911","display_name":"Dick Botteldooren","orcid":"https://orcid.org/0000-0002-7756-7238"},"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":"Dick Botteldooren","raw_affiliation_strings":["Ghent University,Department of Information Technology,Ghent,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University,Department of Information Technology,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007667052","display_name":"Yanjue Song","orcid":"https://orcid.org/0000-0002-9684-6611"},"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":"Yanjue Song","raw_affiliation_strings":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Ghent,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Ghent,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":["Ghent University - imec,IDLab,Department of Electronics and Information Systems,Ghent,Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab,Department of Electronics and Information Systems,Ghent,Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"166","last_page":"171"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12759","display_name":"Vehicle Noise and Vibration Control","score":0.9246000051498413,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12759","display_name":"Vehicle Noise and Vibration Control","score":0.9246000051498413,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9093000292778015,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.7718789577484131},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7121109962463379},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5728741884231567},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5479211807250977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5364845991134644},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.520867109298706},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4574119746685028},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3782464563846588},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3548414707183838}],"concepts":[{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.7718789577484131},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7121109962463379},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5728741884231567},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5479211807250977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5364845991134644},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.520867109298706},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4574119746685028},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3782464563846588},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3548414707183838},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/spa61993.2024.10715626","is_oa":false,"landing_page_url":"https://doi.org/10.23919/spa61993.2024.10715626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01JXZEJR91STGTAWXK0JV8649J","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01JXZEJR91STGTAWXK0JV8649J","pdf_url":"https://biblio.ugent.be/publication/01JXZEJR91STGTAWXK0JV8649J/file/01JXZETQ2F1M8NPF7KW7CR6NAX.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: 9788362065486","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01JXZEJR91STGTAWXK0JV8649J","is_oa":true,"landing_page_url":"http://hdl.handle.net/1854/LU-01JXZEJR91STGTAWXK0JV8649J","pdf_url":"https://biblio.ugent.be/publication/01JXZEJR91STGTAWXK0JV8649J/file/01JXZETQ2F1M8NPF7KW7CR6NAX.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: 9788362065486","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Climate action","id":"https://metadata.un.org/sdg/13","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403511706.pdf","grobid_xml":"https://content.openalex.org/works/W4403511706.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1901129140","https://openalex.org/W2051428568","https://openalex.org/W2052666245","https://openalex.org/W2156232986","https://openalex.org/W2194775991","https://openalex.org/W2291877678","https://openalex.org/W2593116425","https://openalex.org/W2938440247","https://openalex.org/W2959539607","https://openalex.org/W2969163375","https://openalex.org/W3094550259","https://openalex.org/W3211329195","https://openalex.org/W4200337780","https://openalex.org/W4223486923","https://openalex.org/W4365504037","https://openalex.org/W4384557786","https://openalex.org/W4388117217","https://openalex.org/W4388118962","https://openalex.org/W4389200220","https://openalex.org/W4393279815","https://openalex.org/W6631190155","https://openalex.org/W6803516594"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2369710579","https://openalex.org/W4327728159","https://openalex.org/W4394266730","https://openalex.org/W1990856605","https://openalex.org/W2053783616","https://openalex.org/W2545348020","https://openalex.org/W2912751582"],"abstract_inverted_index":{"This":[0,124],"work":[1,76],"addresses":[2],"the":[3,43,57,95,99,110,140,167,194,210],"problem":[4],"of":[5,19,45,47,52,70,83,120,136,146,163,196,202,209],"extracting":[6],"sounds":[7,29,49,88,101],"that":[8,65,109],"are":[9,30,39],"unexpected":[10],"in":[11,129,193],"an":[12,90],"audio":[13,91],"stream":[14],"and":[15,50,150,191,213],"stand":[16],"out":[17],"because":[18],"their":[20,53],"spectrotemporal":[21],"characteristics.":[22],"In":[23,73,139,166],"human":[24],"auditory":[25],"scene":[26],"analysis,":[27],"such":[28],"referred":[31],"to":[32,42,94,116,176],"as":[33],"(sensory)":[34],"salient.":[35],"Previous":[36],"research":[37],"initiatives":[38],"mostly":[40],"limited":[41,115],"detection":[44],"presence":[46],"salient":[48,71,100,121,152,197],"identification":[51],"temporal":[54],"localization":[55],"within":[56],"signal.":[58],"Other":[59],"approaches":[60],"aim":[61],"at":[62,78],"developing":[63,79],"classifiers":[64],"detect":[66],"fixed,":[67],"predetermined":[68],"categories":[69],"sounds.":[72],"contrast,":[74],"this":[75,137],"aims":[77],"a":[80,143,170,182],"solution":[81,212],"capable":[82],"suppressing":[84],"all":[85],"background":[86,148],"(non-salient)":[87],"from":[89],"stream,":[92],"preserving,":[93],"best":[96],"extent":[97],"possible,":[98],"without":[102],"any":[103,117],"distortion.":[104],"An":[105],"additional":[106],"assumption":[107],"is":[108,127,155,189],"algorithm":[111],"should":[112],"not":[113],"be":[114],"particular":[118],"category":[119],"sound":[122,153,198],"events.":[123],"challenging":[125],"task":[126],"realized":[128],"two":[130],"steps,":[131],"both":[132],"being":[133],"novel":[134],"contributions":[135],"work.":[138],"first":[141],"step,":[142,169],"large-scale":[144],"dataset":[145],"clean":[147,151],"samples":[149,154],"created":[156],"by":[157],"automatically":[158],"processing":[159],"publicly":[160],"available":[161],"resource":[162],"field":[164],"recordings.":[165],"second":[168],"deep":[171],"neural":[172],"network":[173],"(U-Net)":[174],"trained":[175],"predict":[177],"complex":[178],"ideal":[179],"ratio":[180],"mask,":[181],"method":[183],"typically":[184],"used":[185],"for":[186,216],"speech":[187],"enhancement,":[188],"adopted":[190],"evaluated":[192],"context":[195],"extraction.":[199],"The":[200],"results":[201],"conducted":[203],"experiments":[204],"indicate":[205,214],"potential":[206],"high":[207],"efficacy":[208],"proposed":[211],"directions":[215],"future":[217],"research.":[218]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}