{"id":"https://openalex.org/W4415708098","doi":"https://doi.org/10.1109/icme59968.2025.11210185","title":"UniSep: Universal Target Audio Separation with Language Models at Scale","display_name":"UniSep: Universal Target Audio Separation with Language Models at Scale","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708098","doi":"https://doi.org/10.1109/icme59968.2025.11210185"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5100423135","display_name":"Yuanyuan Wang","orcid":"https://orcid.org/0000-0001-9472-8606"},"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":true,"raw_author_name":"Yuanyuan Wang","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048946763","display_name":"Hangting Chen","orcid":"https://orcid.org/0000-0002-4085-4364"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangting Chen","raw_affiliation_strings":["Audio and Speech Signal Processing Oteam,Tencent AI Lab,China"],"affiliations":[{"raw_affiliation_string":"Audio and Speech Signal Processing Oteam,Tencent AI Lab,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"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,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113851573","display_name":"Weiqin Li","orcid":null},"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":"Weiqin Li","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632528","display_name":"Dan Luo","orcid":"https://orcid.org/0000-0002-7555-0045"},"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":"Dan Luo","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062105912","display_name":"Guangzhi Li","orcid":"https://orcid.org/0009-0004-9197-7737"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangzhi Li","raw_affiliation_strings":["Audio and Speech Signal Processing Oteam,Tencent AI Lab,China"],"affiliations":[{"raw_affiliation_string":"Audio and Speech Signal Processing Oteam,Tencent AI Lab,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736420","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Yang","raw_affiliation_strings":["Audio and Speech Signal Processing Oteam,Tencent AI Lab,China"],"affiliations":[{"raw_affiliation_string":"Audio and Speech Signal Processing Oteam,Tencent AI Lab,China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"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":"Zhiyong Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"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":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025119324","display_name":"Xixin Wu","orcid":"https://orcid.org/0000-0001-9543-1572"},"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":"Xixin Wu","raw_affiliation_strings":["The Chinese University of Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100423135"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42366032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9271000027656555,"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":0.9271000027656555,"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":0.021900000050663948,"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/T11309","display_name":"Music and Audio Processing","score":0.018400000408291817,"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/source-separation","display_name":"Source separation","score":0.6955999732017517},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.6718999743461609},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6538000106811523},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5501999855041504},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42660000920295715},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4036000072956085},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.4020000100135803},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.39340001344680786},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.38440001010894775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7330999970436096},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6955999732017517},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.6718999743461609},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6538000106811523},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5501999855041504},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46380001306533813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4489000141620636},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.39340001344680786},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.38440001010894775},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.34459999203681946},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.33489999175071716},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.31869998574256897},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28299999237060547},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":26,"referenced_works":["https://openalex.org/W1728888090","https://openalex.org/W2408744528","https://openalex.org/W2593116425","https://openalex.org/W2951130829","https://openalex.org/W2952218014","https://openalex.org/W2962753171","https://openalex.org/W2962866211","https://openalex.org/W2973062255","https://openalex.org/W2990666817","https://openalex.org/W2995181338","https://openalex.org/W2998657200","https://openalex.org/W3037038648","https://openalex.org/W3095410713","https://openalex.org/W3161480375","https://openalex.org/W3161934504","https://openalex.org/W3215615641","https://openalex.org/W4224871700","https://openalex.org/W4226151502","https://openalex.org/W4372260250","https://openalex.org/W4381786045","https://openalex.org/W4385245566","https://openalex.org/W4385822255","https://openalex.org/W4392903555","https://openalex.org/W4392910302","https://openalex.org/W4404317174","https://openalex.org/W4408351785"],"related_works":[],"abstract_inverted_index":{"We":[0,34,110],"propose":[1],"Universal":[2],"target":[3,138],"audio":[4,54,108,120,139],"Separation":[5],"(UniSep),":[6],"addressing":[7],"the":[8,36,53,57,62,87,95,101,113],"separation":[9,37,121,140],"task":[10,38],"on":[11,26],"arbitrary":[12],"mixtures":[13],"of":[14,17,64,89,97,105,115],"different":[15],"types":[16],"audio.":[18],"Distinguished":[19],"from":[20],"previous":[21],"studies,":[22],"UniSep":[23,153],"is":[24,49,79,143],"performed":[25],"unlimited":[27,31],"source":[28,32],"domains":[29],"and":[30,43,93,103,132,157],"numbers.":[33],"formulate":[35],"as":[39],"a":[40,44,75,136,147],"sequence-to-sequence":[41],"problem,":[42],"large":[45],"language":[46],"model":[47,52,141],"(LLM)":[48],"used":[50],"to":[51,81,99,134,146],"sequence":[55],"in":[56,66,118],"discrete":[58],"latent":[59],"space,":[60],"leveraging":[61],"power":[63],"LLM":[65],"handling":[67],"complex":[68],"mixture":[69],"audios":[70],"with":[71,162],"large-scale":[72,90,125],"data.":[73],"Moreover,":[74],"novel":[76],"pre-training":[77],"strategy":[78],"proposed":[80],"utilize":[82],"audio-only":[83],"data,":[84],"which":[85],"reduces":[86],"efforts":[88],"data":[91,126],"simulation":[92],"enhances":[94],"ability":[96],"LLMs":[98],"understand":[100],"consistency":[102],"correlation":[104],"information":[106],"within":[107],"sequences.":[109],"also":[111],"demonstrate":[112],"effectiveness":[114],"scaling":[116],"datasets":[117],"an":[119],"task:":[122],"we":[123],"use":[124],"(36.5k":[127],"hours),":[128],"including":[129],"speech,":[130],"music,":[131],"sound,":[133],"train":[135],"universal":[137],"that":[142,152],"not":[144],"limited":[145],"specific":[148],"domain.":[149],"Experiments":[150],"show":[151],"achieves":[154],"competitive":[155],"subjective":[156],"objective":[158],"evaluation":[159],"results":[160],"compared":[161],"single-task":[163],"models.":[164]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}