{"id":"https://openalex.org/W4392903216","doi":"https://doi.org/10.1109/icassp48485.2024.10447061","title":"Audio Prompt Tuning for Universal Sound Separation","display_name":"Audio Prompt Tuning for Universal Sound Separation","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903216","doi":"https://doi.org/10.1109/icassp48485.2024.10447061"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447061","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/A5103199045","display_name":"Yuzhuo Liu","orcid":"https://orcid.org/0000-0002-8679-8759"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yuzhuo Liu","raw_affiliation_strings":["ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080214850","display_name":"Xubo Liu","orcid":"https://orcid.org/0000-0002-2558-0959"},"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"]},{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Xubo Liu","raw_affiliation_strings":["University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey"],"affiliations":[{"raw_affiliation_string":"University of Surrey,Centre for Vision, Speech and Signal Processing (CVSSP)","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]},{"raw_affiliation_string":"Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey","institution_ids":["https://openalex.org/I28290843","https://openalex.org/I4210121626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111918368","display_name":"Yan Zhao","orcid":"https://orcid.org/0000-0001-8870-742X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Zhao","raw_affiliation_strings":["ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423146","display_name":"Yuanyuan Wang","orcid":"https://orcid.org/0000-0002-2474-5432"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Wang","raw_affiliation_strings":["ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group","Tsinghua University,Shenzhen International Graduate School","Shenzhen International Graduate School, Tsinghua University"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035534911","display_name":"Rui Xia","orcid":"https://orcid.org/0000-0002-0621-1058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Xia","raw_affiliation_strings":["ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093402730","display_name":"Pingchuan Tain","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pingchuan Tain","raw_affiliation_strings":["ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101664515","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0009-0005-3508-3736"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group","Tsinghua University,Shenzhen International Graduate School"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc,Speech, Audio & Music Intelligence (SAMI) Group","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103199045"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8752,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84982332,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1446","last_page":"1450"},"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":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":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.7886664867401123},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7233983874320984},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6508951187133789},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5713789463043213},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5674710869789124},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5263513326644897},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.505033552646637},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4630444645881653},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4565718472003937},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4442089796066284},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4394875168800354},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.42049384117126465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2538837790489197},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.23427951335906982},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11743012070655823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7886664867401123},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7233983874320984},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6508951187133789},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5713789463043213},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5674710869789124},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5263513326644897},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.505033552646637},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4630444645881653},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4565718472003937},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4442089796066284},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4394875168800354},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.42049384117126465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2538837790489197},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.23427951335906982},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11743012070655823},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/icassp48485.2024.10447061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447061","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2951130829","https://openalex.org/W2973062255","https://openalex.org/W3004910802","https://openalex.org/W3043861921","https://openalex.org/W3094550259","https://openalex.org/W3168140565","https://openalex.org/W3197762568","https://openalex.org/W4205991051","https://openalex.org/W4224871700","https://openalex.org/W4226151502","https://openalex.org/W4226442948","https://openalex.org/W4298310324","https://openalex.org/W4310873168","https://openalex.org/W4312651322","https://openalex.org/W4376632781","https://openalex.org/W4385822305","https://openalex.org/W4386075686","https://openalex.org/W6751512325","https://openalex.org/W6766320909","https://openalex.org/W6770984470","https://openalex.org/W6852871851"],"related_works":["https://openalex.org/W2077498359","https://openalex.org/W2289868279","https://openalex.org/W3132176577","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2114974607","https://openalex.org/W4315836293","https://openalex.org/W3112881379","https://openalex.org/W2002298560","https://openalex.org/W2019256813"],"abstract_inverted_index":{"Universal":[0],"sound":[1],"separation":[2,74],"(USS)":[3],"is":[4,42,47],"a":[5,25,39,60,81],"task":[6],"to":[7,65],"separate":[8],"arbitrary":[9,22,36],"sounds":[10,37],"from":[11],"an":[12],"audio":[13,56,89,145],"mixture.":[14],"Existing":[15],"USS":[16,68,97],"systems":[17,151],"are":[18],"capable":[19],"of":[20,28,76,84,95,137,164],"separating":[21,35],"sources,":[23],"given":[24],"few":[26],"examples":[27],"the":[29,45,73,93,96,106,116,122,133,149,157,161],"target":[30],"sources":[31,78],"as":[32],"queries.":[33],"However,":[34],"with":[38,87,115,142],"single":[40],"system":[41],"challenging,":[43],"and":[44,111,129],"robustness":[46],"not":[48],"always":[49],"guaranteed.":[50],"In":[51],"this":[52],"work,":[53],"we":[54],"propose":[55],"prompt":[57,85],"tuning":[58],"(APT),":[59],"simple":[61],"yet":[62],"effective":[63],"approach":[64],"enhance":[66],"existing":[67],"systems.":[69],"Specifically,":[70],"APT":[71,119,141],"improves":[72],"performance":[75,125],"specific":[77],"through":[79],"training":[80,135,154],"small":[82],"number":[83],"parameters":[86,102],"limited":[88],"samples,":[90],"while":[91],"maintaining":[92],"generalization":[94],"model":[98],"by":[99,126],"keeping":[100],"its":[101],"frozen.":[103],"We":[104],"evaluate":[105],"proposed":[107],"method":[108],"on":[109,156],"MUSDB18":[110],"ESC-50":[112,158],"datasets.":[113,139],"Compared":[114],"baseline":[117,150],"model,":[118],"can":[120],"improve":[121],"signal-to-distortion":[123],"ratio":[124],"0.67":[127],"dB":[128,131],"2.06":[130],"using":[132],"full":[134,153],"set":[136],"two":[138],"Moreover,":[140],"only":[143],"5":[144],"samples":[146],"even":[147],"outperforms":[148],"utilizing":[152],"data":[155],"dataset,":[159],"indicating":[160],"great":[162],"potential":[163],"few-shot":[165],"APT.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}