{"id":"https://openalex.org/W4416251096","doi":"https://doi.org/10.1109/waspaa66052.2025.11230943","title":"FasTUSS: Faster Task-Aware Unified Source Separation","display_name":"FasTUSS: Faster Task-Aware Unified Source Separation","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416251096","doi":"https://doi.org/10.1109/waspaa66052.2025.11230943"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5019442580","display_name":"Francesco Paissan","orcid":"https://orcid.org/0000-0002-5553-7935"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Francesco Paissan","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042385500","display_name":"Yoshiki Masuyama","orcid":"https://orcid.org/0000-0002-5881-0474"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoshiki Masuyama","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011355805","display_name":"Ryo Aihara","orcid":"https://orcid.org/0009-0006-6492-3754"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ryo Aihara","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102812631","display_name":"Fran\u00e7ois G. Germain","orcid":"https://orcid.org/0000-0002-8973-5315"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois G. Germain","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079146015","display_name":"Kohei Saijo","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Saijo","raw_affiliation_strings":["Waseda University,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University,Tokyo,Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064097430","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-0158-2837"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5019442580"],"corresponding_institution_ids":["https://openalex.org/I4210159266"],"apc_list":null,"apc_paid":null,"fwci":1.2783,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84976454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"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/T10860","display_name":"Speech and Audio Processing","score":0.9934999942779541,"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":0.9934999942779541,"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":0.0013000000035390258,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.0008999999845400453,"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":0.7224000096321106},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.600600004196167},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5347999930381775},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.486299991607666},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.484499990940094},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.39660000801086426},{"id":"https://openalex.org/keywords/source-model","display_name":"Source model","score":0.32260000705718994}],"concepts":[{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7224000096321106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7053999900817871},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.600600004196167},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5347999930381775},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.484499990940094},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4397999942302704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40549999475479126},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.39660000801086426},{"id":"https://openalex.org/C2985998994","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Source model","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3018999993801117},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26409998536109924},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.25459998846054077}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230943","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230943","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2094721231","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2531409750","https://openalex.org/W2883780447","https://openalex.org/W2951130829","https://openalex.org/W2962753171","https://openalex.org/W2962866211","https://openalex.org/W2963125010","https://openalex.org/W2972541922","https://openalex.org/W2973062255","https://openalex.org/W2990666817","https://openalex.org/W2998657200","https://openalex.org/W3015199127","https://openalex.org/W3042857426","https://openalex.org/W3095263845","https://openalex.org/W3097906045","https://openalex.org/W3160050861","https://openalex.org/W3163652268","https://openalex.org/W3204445636","https://openalex.org/W3205879560","https://openalex.org/W4205689591","https://openalex.org/W4210269029","https://openalex.org/W4210493250","https://openalex.org/W4224871700","https://openalex.org/W4225300878","https://openalex.org/W4226151502","https://openalex.org/W4232282348","https://openalex.org/W4296069305","https://openalex.org/W4297841626","https://openalex.org/W4310873168","https://openalex.org/W4375928773","https://openalex.org/W4379797396","https://openalex.org/W4385756463","https://openalex.org/W4386076539","https://openalex.org/W4387321091","https://openalex.org/W4388979610","https://openalex.org/W4391021752","https://openalex.org/W4392903379","https://openalex.org/W4392903555","https://openalex.org/W4394896659","https://openalex.org/W4402112079","https://openalex.org/W4403126475","https://openalex.org/W4404317174","https://openalex.org/W4408347314"],"related_works":[],"abstract_inverted_index":{"Time-Frequency":[0],"(TF)":[1],"dual-path":[2,104],"models":[3,61],"are":[4,31],"currently":[5],"among":[6],"the":[7,57,75,116,125,139,145,163,189],"best":[8],"performing":[9],"audio":[10,26,89],"source":[11,22,27,80,90],"separation":[12,81,91],"network":[13],"architectures,":[14],"achieving":[15],"state-of-the-art":[16],"performance":[17,173],"in":[18,115],"speech":[19],"enhancement,":[20],"music":[21],"separation,":[23],"and":[24,108,127,159,169,178],"cinematic":[25],"separation.":[28],"While":[29],"they":[30,39],"characterized":[32],"by":[33,56,167],"a":[34,42,48,94,102,119,196],"relatively":[35],"low":[36],"parameter":[37],"count,":[38],"still":[40],"require":[41],"considerable":[43],"number":[44,126],"of":[45,66,118,121,129,142,147,175,191],"operations,":[46],"implying":[47],"higher":[49],"execution":[50],"time.":[51],"This":[52],"problem":[53],"is":[54,98],"exacerbated":[55],"trend":[58],"towards":[59],"bigger":[60],"trained":[62],"on":[63],"large":[64],"amounts":[65],"data":[67],"to":[68,87,131,194],"solve":[69,88],"more":[70,155],"general":[71],"tasks,":[72],"such":[73],"as":[74],"recently":[76],"introduced":[77],"task-aware":[78],"unified":[79],"(TUSS)":[82],"model.":[83,199],"TUSS,":[84],"which":[85],"aims":[86],"tasks":[92],"using":[93],"single,":[95],"conditional":[96],"model,":[97],"built":[99],"upon":[100],"TF-Locoformer,":[101],"TF":[103],"model":[105],"combining":[106],"convolution":[107],"attention":[109],"layers.":[110],"The":[111],"task":[112],"definition":[113],"comes":[114],"form":[117],"sequence":[120],"prompts":[122],"that":[123,161],"specify":[124],"type":[128],"sources":[130],"be":[132],"extracted.":[133],"In":[134],"this":[135],"paper,":[136],"we":[137,187],"analyze":[138],"design":[140],"choices":[141],"TUSS":[143,198],"with":[144,171],"goal":[146],"optimizing":[148],"its":[149],"performance-complexity":[150],"trade-off.":[151],"We":[152],"derive":[153,195],"two":[154],"efficient":[156],"models,":[157],"FasTUSS-8.3G":[158],"FasTUSS-11.7G":[160],"reduce":[162],"original":[164],"model\u2019s":[165],"operations":[166],"81%":[168],"73%":[170],"minor":[172],"drops":[174],"1.2":[176],"dB":[177,180],"0.4":[179],"averaged":[181],"over":[182],"all":[183],"benchmarks,":[184],"respectively.":[185],"Additionally,":[186],"investigate":[188],"impact":[190],"prompt":[192],"conditioning":[193],"causal":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-11-14T00:00:00"}