{"id":"https://openalex.org/W4392904475","doi":"https://doi.org/10.1109/icassp48485.2024.10447219","title":"DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction","display_name":"DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904475","doi":"https://doi.org/10.1109/icassp48485.2024.10447219"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5048171604","display_name":"Jiarui Hai","orcid":"https://orcid.org/0000-0001-9968-7372"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiarui Hai","raw_affiliation_strings":["Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA","Laboratory for Computational Auditory Perception, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Laboratory for Computational Auditory Perception, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101664824","display_name":"Helin Wang","orcid":"https://orcid.org/0000-0001-6088-0378"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Helin Wang","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Baltimore,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,USA","institution_ids":["https://openalex.org/I2799853436","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043555011","display_name":"Dongchao Yang","orcid":"https://orcid.org/0000-0002-8905-224X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongchao Yang","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong SAR,China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong SAR,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078637653","display_name":"Karan Thakkar","orcid":"https://orcid.org/0000-0002-6803-1116"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karan Thakkar","raw_affiliation_strings":["Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA","Laboratory for Computational Auditory Perception, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Laboratory for Computational Auditory Perception, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I2799853436","display_name":"Johns Hopkins Medicine","ror":"https://ror.org/037zgn354","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799853436"]},{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Johns Hopkins University,Center for Language and Speech Processing,Baltimore,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Center for Language and Speech Processing,Baltimore,USA","institution_ids":["https://openalex.org/I2799853436","https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038788686","display_name":"Mounya Elhilali","orcid":"https://orcid.org/0000-0003-2597-738X"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mounya Elhilali","raw_affiliation_strings":["Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA","Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA","Laboratory for Computational Auditory Perception, Johns Hopkins University, Baltimore, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Laboratory for Computational Auditory Perception,Baltimore,USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Laboratory for Computational Auditory Perception, Johns Hopkins University, Baltimore, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048171604"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":2.5784,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89960714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1196","last_page":"1200"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.8026171922683716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767310380935669},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.751885175704956},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6118814945220947},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5600075721740723},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5406913161277771},{"id":"https://openalex.org/keywords/interference","display_name":"Interference (communication)","score":0.5037118792533875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47325068712234497},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4573932886123657},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44570600986480713},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44341447949409485},{"id":"https://openalex.org/keywords/probabilistic-method","display_name":"Probabilistic method","score":0.4222884774208069},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4220430552959442},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4214341640472412},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.32944756746292114}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.8026171922683716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767310380935669},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.751885175704956},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6118814945220947},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5600075721740723},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5406913161277771},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.5037118792533875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47325068712234497},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4573932886123657},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44570600986480713},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44341447949409485},{"id":"https://openalex.org/C60782215","wikidata":"https://www.wikidata.org/wiki/Q3333679","display_name":"Probabilistic method","level":3,"score":0.4222884774208069},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4220430552959442},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4214341640472412},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.32944756746292114},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1713617591","display_name":null,"funder_award_id":"N00014-23-1-2050","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G2392191984","display_name":null,"funder_award_id":"U01AG058532","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5365771482","display_name":null,"funder_award_id":"U01AG058532","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6827979758","display_name":null,"funder_award_id":"N00014-23-1-2086","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2127851351","https://openalex.org/W2593116425","https://openalex.org/W2770119437","https://openalex.org/W2799412098","https://openalex.org/W2964058413","https://openalex.org/W2973062255","https://openalex.org/W3004910802","https://openalex.org/W3015201698","https://openalex.org/W3016038135","https://openalex.org/W3037038648","https://openalex.org/W3092028330","https://openalex.org/W3095263845","https://openalex.org/W3095753917","https://openalex.org/W3158762648","https://openalex.org/W3160506022","https://openalex.org/W3160972914","https://openalex.org/W3178592608","https://openalex.org/W3197762568","https://openalex.org/W3197827948","https://openalex.org/W4221144097","https://openalex.org/W4224914418","https://openalex.org/W4372341629","https://openalex.org/W4372348953","https://openalex.org/W4380434618","https://openalex.org/W4385245566","https://openalex.org/W4385822449","https://openalex.org/W4387512371","https://openalex.org/W4394625831","https://openalex.org/W6746278845","https://openalex.org/W6752516136","https://openalex.org/W6782760101","https://openalex.org/W6783867762","https://openalex.org/W6849109464","https://openalex.org/W6856970790"],"related_works":["https://openalex.org/W4396941953","https://openalex.org/W2093104230","https://openalex.org/W2987280934","https://openalex.org/W4390874210","https://openalex.org/W4384918963","https://openalex.org/W4365211920","https://openalex.org/W2128027845","https://openalex.org/W3014948380","https://openalex.org/W4386184937","https://openalex.org/W4394728283"],"abstract_inverted_index":{"Common":[0],"target":[1,16,31,57,119],"sound":[2,17],"extraction":[3,120],"(TSE)":[4],"approaches":[5,10],"primarily":[6],"relied":[7],"on":[8,43,98],"discriminative":[9],"in":[11,28,113,116],"order":[12],"to":[13,53],"separate":[14],"the":[15,22,30,33,71,99],"while":[18],"minimizing":[19],"interference":[20],"from":[21,32,64],"unwanted":[23,65],"sources,":[24],"with":[25],"varying":[26],"success":[27],"separating":[29],"background.":[34],"This":[35,87],"study":[36],"introduces":[37],"DPM-TSE,":[38],"a":[39,78,110],"generative":[40],"method":[41,80],"based":[42],"diffusion":[44],"probabilistic":[45],"modeling":[46],"(DPM)":[47],"for":[48,81],"Target":[49],"Sound":[50],"Extraction":[51],"(TSE),":[52],"achieve":[54],"both":[55,92],"cleaner":[56],"renderings":[58],"as":[59,61],"well":[60],"improved":[62],"separability":[63],"sounds.":[66],"The":[67,104],"technique":[68],"also":[69],"tackles":[70],"noise":[72,82],"floor":[73],"of":[74,118],"DPM":[75],"by":[76],"introducing":[77],"correction":[79],"schedules":[83],"and":[84,94,121],"sample":[85],"steps.":[86],"approach":[88],"is":[89],"evaluated":[90],"using":[91],"objective":[93],"subjective":[95],"quality":[96,115],"metrics":[97],"FSD":[100],"Kaggle":[101],"2018":[102],"dataset.":[103],"results":[105],"show":[106],"that":[107],"DPM-TSE":[108],"has":[109],"significant":[111],"improvement":[112],"perceived":[114],"terms":[117],"purity.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}