{"id":"https://openalex.org/W4225292962","doi":"https://doi.org/10.1109/icassp43922.2022.9747830","title":"EAD-Conformer: a Conformer-Based Encoder-Attention-Decoder-Network for Multi-Task Audio Source Separation","display_name":"EAD-Conformer: a Conformer-Based Encoder-Attention-Decoder-Network for Multi-Task Audio Source Separation","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225292962","doi":"https://doi.org/10.1109/icassp43922.2022.9747830"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747830","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101744661","display_name":"Chenxing Li","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":"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/A5100322712","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-5344-1884"},"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":"Yang 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":[]}]},{"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":"middle","author":{"id":"https://openalex.org/A5100429710","display_name":"Zhuo Zhang","orcid":"https://orcid.org/0000-0002-6515-0021"},"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":"Zhuo Zhang","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/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":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741750","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0000-0002-9796-488X"},"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":"Zhongyuan 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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127624"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"521","last_page":"525"},"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":0.9994999766349792,"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":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/conformational-isomerism","display_name":"Conformational isomerism","score":0.9061615467071533},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7391828894615173},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7220673561096191},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.594316303730011},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5637785792350769},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5138840675354004},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4398537874221802},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43644657731056213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43121644854545593},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3271993398666382},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08855494856834412},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07785651087760925},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0741698145866394},{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.07249554991722107}],"concepts":[{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.9061615467071533},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7391828894615173},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7220673561096191},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.594316303730011},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5637785792350769},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5138840675354004},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4398537874221802},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43644657731056213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43121644854545593},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3271993398666382},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08855494856834412},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07785651087760925},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0741698145866394},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.07249554991722107},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747830","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2800664709","https://openalex.org/W2892009249","https://openalex.org/W2917831833","https://openalex.org/W2944972166","https://openalex.org/W2952218014","https://openalex.org/W2963242190","https://openalex.org/W2963341071","https://openalex.org/W2963794428","https://openalex.org/W2963925437","https://openalex.org/W2972411915","https://openalex.org/W2990594533","https://openalex.org/W2991361823","https://openalex.org/W3015199127","https://openalex.org/W3090496396","https://openalex.org/W3094938953","https://openalex.org/W3096408984","https://openalex.org/W3096893582","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3161042404","https://openalex.org/W3161140524","https://openalex.org/W3163132306","https://openalex.org/W3163652268","https://openalex.org/W3163827866","https://openalex.org/W3163842642","https://openalex.org/W3177067699","https://openalex.org/W3197042120","https://openalex.org/W3197260772","https://openalex.org/W4210493250","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6754299077","https://openalex.org/W6762182681","https://openalex.org/W6768815455","https://openalex.org/W6783557883"],"related_works":["https://openalex.org/W2023036309","https://openalex.org/W3012606738","https://openalex.org/W1972863456","https://openalex.org/W2089371831","https://openalex.org/W2052399476","https://openalex.org/W2077273959","https://openalex.org/W4385077663","https://openalex.org/W4220905048","https://openalex.org/W2037964119","https://openalex.org/W1494829770"],"abstract_inverted_index":{"In":[0,90],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,58],"Conformer-based":[6,59],"network":[7,37],"to":[8,24,38],"improve":[9],"the":[10,36,51,55,92,98,105],"performance":[11],"of":[12,107],"multi-task":[13],"audio":[14],"source":[15],"separation.":[16],"This":[17],"network,":[18],"named":[19],"EAD-Conformer,":[20,108],"employs":[21],"Conformer":[22],"blocks":[23],"capture":[25],"both":[26],"local":[27],"and":[28,31,71,74,83,126],"global":[29],"information,":[30],"an":[32,62],"encoder-attention-decoder":[33],"manner":[34],"encourages":[35],"perform":[39],"attentive":[40,81],"modeling":[41],"based":[42],"on":[43,120],"different":[44,88,101],"sources.":[45,89,102],"Specifically,":[46],"EAD-Conformer":[47],"first":[48],"parses":[49],"out":[50],"feature":[52],"representations":[53],"from":[54],"mixture":[56],"by":[57],"encoder.":[60],"Then,":[61],"attention":[63],"module":[64],"extracts":[65],"selective":[66],"information":[67],"for":[68,87],"each":[69],"track":[70],"bridges":[72],"encoder":[73],"decoders.":[75],"Finally,":[76],"three":[77],"decoders":[78],"respectively":[79],"process":[80],"features":[82],"generate":[84],"output":[85],"masks":[86],"addition,":[91],"proposed":[93],"discriminate":[94],"loss":[95],"further":[96],"enlarges":[97],"distance":[99],"between":[100],"Experiments":[103],"demonstrate":[104],"effectiveness":[106],"which":[109],"achieves":[110],"13.37":[111],"dB,":[112,114],"11.41":[113],"10.56":[115],"dB":[116],"signal-to-distortion":[117],"ratio":[118],"improvement":[119],"speech,":[121],"music,":[122],"noise":[123],"track,":[124],"respectively,":[125],"shows":[127],"advantages":[128],"over":[129],"several":[130],"well-known":[131],"models.":[132]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}