{"id":"https://openalex.org/W4403127034","doi":"https://doi.org/10.1109/iwaenc61483.2024.10693958","title":"Gaussian Flow Bridges for Audio Domain Transfer with Unpaired Data","display_name":"Gaussian Flow Bridges for Audio Domain Transfer with Unpaired Data","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4403127034","doi":"https://doi.org/10.1109/iwaenc61483.2024.10693958"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc61483.2024.10693958","doi":"https://doi.org/10.1109/iwaenc61483.2024.10693958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10693958","pdf_url":null,"source":{"id":"https://openalex.org/S4306420272","display_name":"International Workshop on Acoustic Signal Enhancement","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.19497","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030929567","display_name":"Eloi Moliner","orcid":"https://orcid.org/0000-0001-5719-326X","observed_orcids":["https://orcid.org/0000-0001-5719-326X"]},"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":"Eloi Moliner","raw_affiliation_strings":["Acoustics Lab, DICE Aalto University,Espoo,Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Acoustics Lab, DICE Aalto University,Espoo,Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055277441","display_name":"Sebastian Braun","orcid":"https://orcid.org/0000-0001-9060-223X","observed_orcids":["https://orcid.org/0000-0001-9060-223X"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian Braun","raw_affiliation_strings":["Microsoft Research Redmond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Redmond","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036868085","display_name":"Hannes Gamper","orcid":"https://orcid.org/0000-0002-2148-6367","observed_orcids":["https://orcid.org/0000-0002-2148-6367"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hannes Gamper","raw_affiliation_strings":["Microsoft Research Redmond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Redmond","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3816,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55891739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"374","last_page":"378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.4058000147342682,"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":0.4058000147342682,"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":0.3127000033855438,"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":0.2167000025510788,"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/unpaired-data","display_name":"unpaired data","score":0.8029999732971191},{"id":"https://openalex.org/keywords/optimal-transport","display_name":"optimal transport","score":0.6200000047683716},{"id":"https://openalex.org/keywords/reverberation-removal","display_name":"reverberation removal","score":0.5580000281333923},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.46399998664855957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6413642168045044},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.45580223202705383},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4547036588191986},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.44310641288757324},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3534332513809204},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10980668663978577},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10154557228088379},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07682719826698303},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iwaenc61483.2024.10693958","doi":"https://doi.org/10.1109/iwaenc61483.2024.10693958","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc61483.2024.10693958","pdf_url":null,"source":{"id":"https://openalex.org/S4306420272","display_name":"International Workshop on Acoustic Signal Enhancement","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2024 18th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2405.19497","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.19497","pdf_url":"https://arxiv.org/pdf/2405.19497","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.19497","doi":"https://doi.org/10.48550/arxiv.2405.19497","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.19497","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.19497","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.19497","pdf_url":"https://arxiv.org/pdf/2405.19497","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403127034.pdf","grobid_xml":"https://content.openalex.org/works/W4403127034.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1557831657","https://openalex.org/W1968834101","https://openalex.org/W1989314204","https://openalex.org/W2013139519","https://openalex.org/W2074604179","https://openalex.org/W2086381917","https://openalex.org/W2172491908","https://openalex.org/W2222562092","https://openalex.org/W2555915854","https://openalex.org/W2900429685","https://openalex.org/W2901243971","https://openalex.org/W2902070858","https://openalex.org/W3036167779","https://openalex.org/W3097627357","https://openalex.org/W3152626170","https://openalex.org/W3167139504","https://openalex.org/W3207551191","https://openalex.org/W3214314684","https://openalex.org/W3215290109","https://openalex.org/W3215881519","https://openalex.org/W3217317857","https://openalex.org/W4221146626","https://openalex.org/W4288099666","https://openalex.org/W4293192231","https://openalex.org/W4297676498","https://openalex.org/W4303647933","https://openalex.org/W4311000453","https://openalex.org/W4312779270","https://openalex.org/W4318719691","https://openalex.org/W4319050105","https://openalex.org/W4367832869","https://openalex.org/W4372259754","https://openalex.org/W4372341905","https://openalex.org/W4375868955","https://openalex.org/W4384080510","https://openalex.org/W4386076532","https://openalex.org/W4391901138","https://openalex.org/W6772349387","https://openalex.org/W6795007937"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Audio":[0],"domain":[1],"transfer":[2],"is":[3],"the":[4,19,37,56,66,82,97,117,159],"process":[5],"of":[6,13,39,62,68,71,81,96,133,151],"modifying":[7],"audio":[8,29,63],"signals":[9,64],"to":[10],"match":[11],"characteristics":[12],"a":[14,69,87,93,123],"different":[15,60],"domain,":[16],"while":[17],"retaining":[18],"original":[20],"content.":[21],"Examples":[22],"include":[23],"transferring":[24],"room":[25],"acoustics":[26],"or":[27],"altering":[28],"effects":[30],"such":[31],"as":[32],"distortion.":[33],"This":[34],"paper":[35],"investigates":[36],"potential":[38,167],"Gaussian":[40],"Flow":[41],"Bridges,":[42],"an":[43],"emerging":[44],"approach":[45,102],"in":[46,149,163],"generative":[47],"modeling,":[48],"for":[49,109,168],"these":[50],"problems.":[51],"The":[52,76],"presented":[53],"framework":[54,78],"addresses":[55],"transport":[57],"problem":[58],"across":[59],"distributions":[61],"through":[65,86],"implementation":[67],"series":[70],"two":[72],"deterministic":[73],"probability":[74],"flows.":[75],"proposed":[77],"facilitates":[79],"manipulation":[80],"target":[83,98],"distribution":[84],"properties":[85],"continuous":[88],"control":[89],"variable,":[90],"which":[91],"defines":[92],"certain":[94],"aspect":[95],"domain.":[99],"Notably,":[100],"this":[101,164],"does":[103],"not":[104],"rely":[105],"on":[106,115],"paired":[107],"examples":[108],"training.":[110],"To":[111],"address":[112],"identified":[113],"challenges":[114],"maintaining":[116],"speech":[118],"content":[119],"consistent,":[120],"we":[121,145],"recommend":[122],"training":[124],"strategy":[125],"that":[126],"incorporates":[127],"chunk-based":[128],"minibatch":[129],"Optimal":[130],"Transport":[131],"couplings":[132],"data":[134],"samples":[135],"and":[136,153],"noise.":[137],"Comparing":[138],"our":[139],"unsupervised":[140],"method":[141],"with":[142],"established":[143],"baselines,":[144],"find":[146],"competitive":[147],"performance":[148],"tasks":[150],"reverberation":[152],"distortion":[154],"manipulation.":[155],"Despite":[156],"encoutering":[157],"limitations,":[158],"intriguing":[160],"results":[161],"obtained":[162],"study":[165],"underscore":[166],"further":[169],"exploration.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}