{"id":"https://openalex.org/W4210493250","doi":"https://doi.org/10.1109/asru51503.2021.9687922","title":"Multi-Task Audio Source Separation","display_name":"Multi-Task Audio Source Separation","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210493250","doi":"https://doi.org/10.1109/asru51503.2021.9687922"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687922","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100388629","display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0002-3469-2899"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210127624","display_name":"Shougang Institute of Technology","ror":"https://ror.org/03agmnc67","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210127624"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["Kuai Shou Technology Co.,Beijing,China","Harbin Institute of Technology, Shenzhen, China","Kuai Shou Technology Co., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuai Shou Technology Co.,Beijing,China","institution_ids":["https://openalex.org/I4210127624"]},{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Kuai Shou Technology Co., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050682332","display_name":"Chenxing Li","orcid":"https://orcid.org/0000-0002-3997-8212"},"institutions":[{"id":"https://openalex.org/I4210127624","display_name":"Shougang Institute of Technology","ror":"https://ror.org/03agmnc67","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210127624"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenxing Li","raw_affiliation_strings":["Kuai Shou Technology Co.,Beijing,China","Kuai Shou Technology Co., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuai Shou Technology Co.,Beijing,China","institution_ids":["https://openalex.org/I4210127624"]},{"raw_affiliation_string":"Kuai Shou Technology Co., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101374328","display_name":"Feng Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127624","display_name":"Shougang Institute of Technology","ror":"https://ror.org/03agmnc67","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210127624"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Deng","raw_affiliation_strings":["Kuai Shou Technology Co.,Beijing,China","Kuai Shou Technology Co., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuai Shou Technology Co.,Beijing,China","institution_ids":["https://openalex.org/I4210127624"]},{"raw_affiliation_string":"Kuai Shou Technology Co., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I4210127624","display_name":"Shougang Institute of Technology","ror":"https://ror.org/03agmnc67","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210127624"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["Kuai Shou Technology Co.,Beijing,China","Kuai Shou Technology Co., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuai Shou Technology Co.,Beijing,China","institution_ids":["https://openalex.org/I4210127624"]},{"raw_affiliation_string":"Kuai Shou Technology Co., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"671","last_page":"678"},"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":0.9987999796867371,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.811508059501648},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7429861426353455},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.737929105758667},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6977183222770691},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5079053044319153},{"id":"https://openalex.org/keywords/blind-signal-separation","display_name":"Blind signal separation","score":0.49774840474128723},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4958735406398773},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47835081815719604},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.43462252616882324},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4301831126213074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41936928033828735},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41319340467453003},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41174525022506714},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3455660343170166},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15262293815612793},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.11829811334609985}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.811508059501648},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7429861426353455},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.737929105758667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6977183222770691},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5079053044319153},{"id":"https://openalex.org/C120317606","wikidata":"https://www.wikidata.org/wiki/Q17105967","display_name":"Blind signal separation","level":3,"score":0.49774840474128723},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4958735406398773},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47835081815719604},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43462252616882324},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4301831126213074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41936928033828735},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41319340467453003},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41174525022506714},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3455660343170166},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15262293815612793},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.11829811334609985},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","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/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/asru51503.2021.9687922","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687922","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W2044893557","https://openalex.org/W2095705004","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2800664709","https://openalex.org/W2903502793","https://openalex.org/W2938709889","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2963242190","https://openalex.org/W2963751183","https://openalex.org/W2963992487","https://openalex.org/W2972411915","https://openalex.org/W2985214749","https://openalex.org/W2990594533","https://openalex.org/W2990666817","https://openalex.org/W2991361823","https://openalex.org/W2998657200","https://openalex.org/W3015199127","https://openalex.org/W3017350693","https://openalex.org/W3090496396","https://openalex.org/W3095868011","https://openalex.org/W3096408984","https://openalex.org/W3096893582","https://openalex.org/W3097817799","https://openalex.org/W3099330747","https://openalex.org/W3160050861","https://openalex.org/W3160085755","https://openalex.org/W3161042404","https://openalex.org/W3161140524","https://openalex.org/W3163132306","https://openalex.org/W3163464523","https://openalex.org/W3163827866","https://openalex.org/W3163842642","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6759591289","https://openalex.org/W6783557883"],"related_works":["https://openalex.org/W2103031592","https://openalex.org/W1967226023","https://openalex.org/W2538939196","https://openalex.org/W3045520545","https://openalex.org/W3150394233","https://openalex.org/W2289868279","https://openalex.org/W3112881379","https://openalex.org/W2002298560","https://openalex.org/W2019256813","https://openalex.org/W2158216966"],"abstract_inverted_index":{"The":[0,22,145,162],"audio":[1,43,101,118],"source":[2,13,44],"separation":[3,45,169,174],"tasks,":[4],"such":[5],"as":[6,137],"speech":[7,9],"enhancement,":[8],"separation,":[10,14],"and":[11,53,68,77,120],"music":[12],"have":[15],"achieved":[16],"impressive":[17],"performance":[18,170],"in":[19,86,95,168],"recent":[20],"studies.":[21],"powerful":[23],"modeling":[24],"capabilities":[25],"of":[26,65,72,98,117],"deep":[27],"neural":[28],"networks":[29],"give":[30],"us":[31],"hope":[32],"for":[33,142],"more":[34,139],"challenging":[35],"tasks.":[36],"This":[37],"paper":[38],"launches":[39],"a":[40,70,109,138],"new":[41],"multi-task":[42],"(MTASS)":[46],"challenge":[47],"to":[48,90,157],"separate":[49],"the":[50,57,63,87,93,99,105,114,131,143,151,159],"speech,":[51,75],"music,":[52,76],"noise":[54],"signals":[55,119,160],"from":[56],"monaural":[58],"mixture.":[59],"First,":[60],"we":[61,81],"introduce":[62],"details":[64],"this":[66],"task":[67],"generate":[69],"dataset":[71],"mixtures":[73],"containing":[74],"background":[78],"noises.":[79],"Then,":[80],"propose":[82],"an":[83],"MTASS":[84],"model":[85,107,164],"complex":[88,132],"domain":[89],"fully":[91],"utilize":[92],"differences":[94],"spectral":[96],"characteristics":[97],"three":[100,115],"signals.":[102],"In":[103],"detail,":[104],"proposed":[106,163],"follows":[108],"two-stage":[110],"pipeline,":[111],"which":[112],"separates":[113],"types":[116],"then":[121],"performs":[122],"signal":[123,153],"compensation":[124,154],"separately.":[125],"After":[126],"comparing":[127],"different":[128],"training":[129],"targets,":[130],"ratio":[133],"mask":[134],"is":[135],"selected":[136],"suitable":[140],"target":[141],"MTASS.":[144],"experimental":[146],"results":[147],"also":[148],"indicate":[149],"that":[150],"residual":[152],"module":[155],"helps":[156],"recover":[158],"further.":[161],"shows":[165],"significant":[166],"advantages":[167],"over":[171],"several":[172],"well-known":[173],"models.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}