{"id":"https://openalex.org/W3163652268","doi":"https://doi.org/10.1109/icassp39728.2021.9413901","title":"Attention Is All You Need In Speech Separation","display_name":"Attention Is All You Need In Speech Separation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163652268","doi":"https://doi.org/10.1109/icassp39728.2021.9413901","mag":"3163652268"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5023830739","display_name":"Cem Subakan","orcid":"https://orcid.org/0000-0002-7593-6589"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Cem Subakan","raw_affiliation_strings":["Mila-Quebec AI Institute, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila-Quebec AI Institute, Canada","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102962935","display_name":"Mirco Ravanelli","orcid":"https://orcid.org/0000-0001-8479-3121"},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mirco Ravanelli","raw_affiliation_strings":["Mila-Quebec AI Institute, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila-Quebec AI Institute, Canada","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047682990","display_name":"Samuele Cornell","orcid":"https://orcid.org/0000-0002-5358-1844"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Samuele Cornell","raw_affiliation_strings":["Universit\u00e0 Politecnica delle Marche, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Politecnica delle Marche, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028787566","display_name":"Mirko Bronzi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mirko Bronzi","raw_affiliation_strings":["Mila-Quebec AI Institute, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila-Quebec AI Institute, Canada","institution_ids":["https://openalex.org/I4210164802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063943539","display_name":"Jianyuan Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianyuan Zhong","raw_affiliation_strings":["University of Rochester, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Rochester, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":62.0375,"has_fulltext":false,"cited_by_count":613,"citation_normalized_percentile":{"value":0.99973226,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"25"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/computer-science","display_name":"Computer science","score":0.8041918277740479},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7707247734069824},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7162197828292847},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6354981660842896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48037558794021606},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.453741192817688},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3888494074344635},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37881630659103394},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20329898595809937},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0864400863647461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041918277740479},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7707247734069824},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7162197828292847},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6354981660842896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48037558794021606},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.453741192817688},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3888494074344635},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37881630659103394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20329898595809937},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0864400863647461},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2064675550","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2734774145","https://openalex.org/W2794209590","https://openalex.org/W2903739847","https://openalex.org/W2952218014","https://openalex.org/W2962935966","https://openalex.org/W2963317762","https://openalex.org/W2963403868","https://openalex.org/W2963443859","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2972460025","https://openalex.org/W2972818416","https://openalex.org/W2981436548","https://openalex.org/W2981608174","https://openalex.org/W2996969697","https://openalex.org/W3007328579","https://openalex.org/W3008880747","https://openalex.org/W3015199127","https://openalex.org/W3015834770","https://openalex.org/W3016129867","https://openalex.org/W3035268204","https://openalex.org/W3036475981","https://openalex.org/W3042857426","https://openalex.org/W3094607766","https://openalex.org/W3095717210","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3104896896","https://openalex.org/W3185109982","https://openalex.org/W4287632494","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6745149982","https://openalex.org/W6759323020","https://openalex.org/W6768815455","https://openalex.org/W6769530546","https://openalex.org/W6774687970","https://openalex.org/W6774995033","https://openalex.org/W6779304837","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W7958345","https://openalex.org/W2279739","https://openalex.org/W14899464","https://openalex.org/W3011399","https://openalex.org/W4354089","https://openalex.org/W8459508","https://openalex.org/W6882942","https://openalex.org/W13529535","https://openalex.org/W6452702","https://openalex.org/W5683847"],"abstract_inverted_index":{"Recurrent":[0],"Neural":[1],"Networks":[2],"(RNNs)":[3],"have":[4],"long":[5],"been":[6],"the":[7,49,82,106,119,138],"dominant":[8],"architecture":[9],"in":[10],"sequence-to-sequence":[11],"learning.":[12],"RNNs,":[13,36],"however,":[14],"are":[15,28],"inherently":[16],"sequential":[17],"models":[18],"that":[19,71],"do":[20],"not":[21],"allow":[22],"parallelization":[23,107],"of":[24,90,98,109,125],"their":[25],"computations.":[26],"Transformers":[27,110],"emerging":[29],"as":[30],"a":[31,41,51,68,113,123],"natural":[32],"alternative":[33],"to":[34],"standard":[35,83],"replacing":[37],"recurrent":[38],"computations":[39],"with":[40,67,143],"multi-head":[42],"attention":[43],"mechanism.In":[44],"this":[45],"paper,":[46],"we":[47],"propose":[48],"SepFormer,":[50],"novel":[52],"RNN-free":[53],"Transformer-based":[54],"neural":[55],"network":[56],"for":[57],"speech":[58,140],"separation.":[59],"The":[60,74,103],"Sep-Former":[61],"learns":[62],"short":[63],"and":[64,95,111,132],"long-term":[65],"dependencies":[66],"multi-scale":[69],"approach":[70],"employs":[72],"transformers.":[73],"proposed":[75],"model":[76],"achieves":[77,112],"state-of-the-art":[78],"(SOTA)":[79],"performance":[80,115],"on":[81,93,101],"WSJ0-2/3mix":[84],"datasets.":[85],"It":[86,127],"reaches":[87],"an":[88,96],"SI-SNRi":[89,97],"22.3":[91],"dB":[92,100],"WSJ0-2mix":[94],"19.5":[99],"WSJ0-3mix.":[102],"SepFormer":[104],"inherits":[105],"advantages":[108],"competitive":[114],"even":[116],"when":[117],"downsampling":[118],"encoded":[120],"representation":[121],"by":[122],"factor":[124],"8.":[126],"is":[128,134],"thus":[129],"significantly":[130],"faster":[131],"it":[133],"less":[135],"memory-demanding":[136],"than":[137],"latest":[139],"separation":[141],"systems":[142],"comparable":[144],"performance.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":36},{"year":2025,"cited_by_count":174},{"year":2024,"cited_by_count":152},{"year":2023,"cited_by_count":136},{"year":2022,"cited_by_count":88},{"year":2021,"cited_by_count":26},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-19T17:40:00.097472","created_date":"2025-10-10T00:00:00"}