{"id":"https://openalex.org/W3177067699","doi":"https://doi.org/10.1109/waspaa52581.2021.9632794","title":"DF-Conformer: Integrated Architecture of Conv-Tasnet and Conformer Using Linear Complexity Self-Attention for Speech Enhancement","display_name":"DF-Conformer: Integrated Architecture of Conv-Tasnet and Conformer Using Linear Complexity Self-Attention for Speech Enhancement","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3177067699","doi":"https://doi.org/10.1109/waspaa52581.2021.9632794","mag":"3177067699"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa52581.2021.9632794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuma Koizumi","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036532214","display_name":"Shigeki Karita","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shigeki Karita","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053447215","display_name":"Scott Wisdom","orcid":"https://orcid.org/0000-0001-6671-1428"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Wisdom","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hakan Erdogan","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023448834","display_name":"Llion Jones","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Llion Jones","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"165"},"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":0.9983000159263611,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9972000122070312,"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":0.7093499898910522},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.658475399017334},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5488643050193787},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46067604422569275},{"id":"https://openalex.org/keywords/conformational-isomerism","display_name":"Conformational isomerism","score":0.4560927450656891},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.433937668800354},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3522348701953888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33449965715408325},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1813744604587555},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12686753273010254}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7093499898910522},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.658475399017334},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5488643050193787},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46067604422569275},{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.4560927450656891},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.433937668800354},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3522348701953888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33449965715408325},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1813744604587555},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12686753273010254},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa52581.2021.9632794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa52581.2021.9632794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W2516001803","https://openalex.org/W2517616541","https://openalex.org/W2805233667","https://openalex.org/W2890553422","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963189033","https://openalex.org/W2963403868","https://openalex.org/W2964058413","https://openalex.org/W2964121744","https://openalex.org/W2964171275","https://openalex.org/W2964207404","https://openalex.org/W2998657200","https://openalex.org/W3004940340","https://openalex.org/W3011424113","https://openalex.org/W3015219411","https://openalex.org/W3015312544","https://openalex.org/W3025165719","https://openalex.org/W3034573343","https://openalex.org/W3037798801","https://openalex.org/W3048833027","https://openalex.org/W3085139254","https://openalex.org/W3093839391","https://openalex.org/W3095717210","https://openalex.org/W3096431533","https://openalex.org/W3096893582","https://openalex.org/W3097777922","https://openalex.org/W3099330747","https://openalex.org/W3100954996","https://openalex.org/W3103619082","https://openalex.org/W3125056032","https://openalex.org/W3127985485","https://openalex.org/W3151851237","https://openalex.org/W3160044950","https://openalex.org/W3160129476","https://openalex.org/W3161950572","https://openalex.org/W3163114796","https://openalex.org/W3163464523","https://openalex.org/W3163652268","https://openalex.org/W3163842642","https://openalex.org/W4287632494","https://openalex.org/W4287667694","https://openalex.org/W4309793872","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6779709467","https://openalex.org/W6783944145","https://openalex.org/W6784429643","https://openalex.org/W6784499681"],"related_works":["https://openalex.org/W2023036309","https://openalex.org/W1972863456","https://openalex.org/W2089371831","https://openalex.org/W2052399476","https://openalex.org/W2810163160","https://openalex.org/W3083970380","https://openalex.org/W2037964119","https://openalex.org/W4385077663","https://openalex.org/W2161045342","https://openalex.org/W2943002782"],"abstract_inverted_index":{"Single-channel":[0],"speech":[1,9,103],"enhancement":[2],"(SE)":[3],"is":[4],"an":[5,16,135],"important":[6],"task":[7],"in":[8],"processing.":[10],"A":[11],"widely":[12],"used":[13],"framework":[14],"combines":[15],"anal-ysis/synthesis":[17],"filterbank":[18],"with":[19],"a":[20,68],"mask":[21,46,70],"prediction":[22,47,71],"network,":[23],"such":[24,30],"as":[25],"the":[26,32,42,45,56,75,81,96,109,129],"Conv-TasNet":[27,61],"architecture.":[28],"In":[29,49],"systems,":[31],"denoising":[33],"performance":[34],"and":[35,87,105,119],"computational":[36,117],"efficiency":[37],"are":[38],"mainly":[39],"affected":[40],"by":[41,63],"structure":[43],"of":[44,60,101,111,138],"network.":[48,72],"this":[50],"study,":[51],"we":[52,79],"aim":[53],"to":[54],"improve":[55],"sequential":[57],"modeling":[58],"ability":[59],"architectures":[62],"integrating":[64],"Conformer":[65,82],"layers":[66],"into":[67],"new":[69],"To":[73],"make":[74],"model":[76,97,122],"computationally":[77],"feasible,":[78],"extend":[80],"using":[83],"linear":[84,112],"complexity":[85,113],"attention":[86,114],"stacked":[88],"1-D":[89],"dilated":[90],"depthwise":[91],"convolution":[92,132],"layers.":[93],"We":[94],"trained":[95],"on":[98],"3,396":[99],"hours":[100],"noisy":[102],"data,":[104],"show":[106],"that":[107],"(i)":[108],"use":[110],"avoids":[115],"high":[116],"complexity,":[118],"(ii)":[120],"our":[121],"achieves":[123],"higher":[124],"scale-invariant":[125],"signal-to-noise":[126],"ratio":[127],"than":[128],"improved":[130],"time-dilated":[131],"network":[133],"(TDCN++),":[134],"extended":[136],"version":[137],"Conv-TasNet.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}