{"id":"https://openalex.org/W4408352385","doi":"https://doi.org/10.1109/icassp49660.2025.10890129","title":"FlowSep: Language-Queried Sound Separation with Rectified Flow Matching","display_name":"FlowSep: Language-Queried Sound Separation with Rectified Flow Matching","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352385","doi":"https://doi.org/10.1109/icassp49660.2025.10890129"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5101889011","display_name":"Yi Yuan","orcid":"https://orcid.org/0000-0002-7121-0983"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yi Yuan","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407730","display_name":"Xubo Liu","orcid":"https://orcid.org/0009-0004-9950-2672"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089924305","display_name":"Haohe Liu","orcid":"https://orcid.org/0000-0003-1036-7888"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haohe Liu","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066967599","display_name":"Mark D. Plumbley","orcid":"https://orcid.org/0000-0002-9708-1075"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark D. Plumbley","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,UK","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,UK"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP),Guildford,UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101889011"],"corresponding_institution_ids":["https://openalex.org/I28290843"],"apc_list":null,"apc_paid":null,"fwci":6.2972,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95970346,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.7222411036491394},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.46536707878112793},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.4611049294471741},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46019792556762695},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4288980960845947},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.21932637691497803},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11505323648452759},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0653301477432251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222411036491394},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.46536707878112793},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.4611049294471741},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46019792556762695},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4288980960845947},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.21932637691497803},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11505323648452759},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0653301477432251},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890129","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2052666245","https://openalex.org/W2593116425","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2972478942","https://openalex.org/W3016000368","https://openalex.org/W3094550259","https://openalex.org/W3094893721","https://openalex.org/W3095263845","https://openalex.org/W4224871700","https://openalex.org/W4224914418","https://openalex.org/W4372260310","https://openalex.org/W4392903216","https://openalex.org/W4392904475","https://openalex.org/W4392909497","https://openalex.org/W4392909615","https://openalex.org/W4396877837","https://openalex.org/W4400033239","https://openalex.org/W4403780831","https://openalex.org/W6637373629","https://openalex.org/W6755207826","https://openalex.org/W6769627184","https://openalex.org/W6791353385","https://openalex.org/W6801426729","https://openalex.org/W6838843145","https://openalex.org/W6843731886","https://openalex.org/W6849109464","https://openalex.org/W6851290578","https://openalex.org/W6859583170","https://openalex.org/W6869897819"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Language-queried":[0],"audio":[1,155,195],"source":[2,115,196],"separation":[3,185,197],"(LASS)":[4],"focuses":[5],"on":[6,101,150],"separating":[7,42],"sounds":[8,29],"using":[9],"textual":[10],"descriptions":[11],"of":[12,71,154],"the":[13,69,118,126,136,147,159],"desired":[14],"sources.":[15,35],"Current":[16],"methods":[17],"mainly":[18],"use":[19],"discriminative":[20],"approaches,":[21],"such":[22,50],"as":[23,51,165],"time-frequency":[24],"masking,":[25],"to":[26,48,113,145],"separate":[27],"target":[28,114],"and":[30,73,79,169,187,202],"minimize":[31],"interference":[32],"from":[33,111],"other":[34],"However,":[36],"these":[37],"models":[38,161,201],"face":[39],"challenges":[40],"when":[41],"overlapping":[43],"sound-tracks,":[44],"which":[45],"may":[46],"lead":[47],"artifacts":[49],"spectral":[52],"holes":[53],"or":[54],"incomplete":[55],"separation.":[56,89],"Rectified":[57],"flow":[58,109],"matching":[59],"(RFM),":[60],"a":[61,96,133,142,179],"generative":[62,98],"model":[63,99,182],"that":[64,176],"establishes":[65],"linear":[66,108],"relations":[67],"between":[68],"distribution":[70],"data":[72],"noise,":[74],"offers":[75],"superior":[76],"theoretical":[77],"properties":[78],"simplicity,":[80],"but":[81],"has":[82],"not":[83],"yet":[84],"been":[85],"explored":[86],"in":[87,183],"sound":[88],"In":[90],"this":[91],"work,":[92],"we":[93],"introduce":[94],"FlowSep,":[95],"new":[97],"based":[100],"RFM":[102],"for":[103,194],"LASS":[104,181],"tasks.":[105,198],"FlowSep":[106,157,177],"learns":[107],"trajectories":[110],"noise":[112],"features":[116,129],"within":[117],"variational":[119],"autoencoder":[120],"(VAE)":[121],"latent":[122,128],"space.":[123],"During":[124],"inference,":[125],"RFM-generated":[127],"are":[130],"reconstructed":[131],"into":[132],"mel-spectrogram":[134],"via":[135],"pre-trained":[137,143,200],"VAE":[138],"decoder,":[139],"followed":[140],"by":[141],"vocoder":[144],"synthesize":[146],"waveform.":[148],"Trained":[149],"1,":[151],"680":[152],"hours":[153],"data,":[156],"outperforms":[158],"state-of-the-art":[160],"across":[162],"multiple":[163],"benchmarks,":[164],"evaluated":[166],"with":[167],"subjective":[168],"objective":[170],"metrics.":[171],"Additionally,":[172],"our":[173],"results":[174],"show":[175],"surpasses":[178],"diffusion-based":[180],"both":[184],"quality":[186],"inference":[188],"efficiency,":[189],"highlighting":[190],"its":[191],"strong":[192],"potential":[193],"Code,":[199],"demos":[203],"can":[204],"be":[205],"found":[206],"at:":[207],"https://audio-agi.github.io/FlowSep_demo/.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}