{"id":"https://openalex.org/W2982208454","doi":"https://doi.org/10.1109/icassp40776.2020.9053038","title":"Filterbank Design for End-to-end Speech Separation","display_name":"Filterbank Design for End-to-end Speech Separation","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2982208454","doi":"https://doi.org/10.1109/icassp40776.2020.9053038","mag":"2982208454"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.10400","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061902495","display_name":"Manuel Pariente","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Manuel Pariente","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","Speech Modeling for Facilitating Oral-Based Communication"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Speech Modeling for Facilitating Oral-Based Communication","institution_ids":[]}]},{"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":["Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Italy","Universit\u00e0 Politecnica delle Marche,Department of Information Engineering,Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Italy","institution_ids":["https://openalex.org/I122534668"]},{"raw_affiliation_string":"Universit\u00e0 Politecnica delle Marche,Department of Information Engineering,Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000981106","display_name":"Antoine Deleforge","orcid":"https://orcid.org/0000-0003-0339-7472"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Deleforge","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","Speech Modeling for Facilitating Oral-Based Communication"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Speech Modeling for Facilitating Oral-Based Communication","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065635001","display_name":"Emmanuel Vincent","orcid":"https://orcid.org/0000-0002-0183-7289"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Vincent","raw_affiliation_strings":["Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","Speech Modeling for Facilitating Oral-Based Communication"],"affiliations":[{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Inria, LORIA, Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I4210121838","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Speech Modeling for Facilitating Oral-Based Communication","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061902495"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838","https://openalex.org/I90183372"],"apc_list":null,"apc_paid":null,"fwci":0.1523,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.39002357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6364","last_page":"6368"},"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":0.9998000264167786,"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":0.9995999932289124,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7783827781677246},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.5555049180984497},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5107371807098389},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39325302839279175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13067874312400818}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7783827781677246},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.5555049180984497},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5107371807098389},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39325302839279175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13067874312400818},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053038","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053038","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.10400","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10400","pdf_url":"https://arxiv.org/pdf/1910.10400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-02355623v1","is_oa":true,"landing_page_url":"https://hal.archives-ouvertes.fr/hal-02355623","pdf_url":null,"source":null,"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.archives-ouvertes.fr/hal-02355623","raw_type":"info:eu-repo/semantics/preprint"},{"id":"pmh:oai:HAL:hal-02355623v2","is_oa":true,"landing_page_url":"https://hal.science/hal-02355623","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2020 - 45th International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.1910.10400","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.10400","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/e0bt-8j10","is_oa":true,"landing_page_url":"https://doi.org/10.17023/e0bt-8j10","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.10400","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10400","pdf_url":"https://arxiv.org/pdf/1910.10400","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1897240248","https://openalex.org/W2026795768","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2558649592","https://openalex.org/W2734774145","https://openalex.org/W2784225997","https://openalex.org/W2891405874","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962935966","https://openalex.org/W2964052309","https://openalex.org/W2964058413","https://openalex.org/W2964153283","https://openalex.org/W2968917279","https://openalex.org/W2972541922","https://openalex.org/W2973053574","https://openalex.org/W2973054567","https://openalex.org/W2973143779","https://openalex.org/W2981976899","https://openalex.org/W6631190155","https://openalex.org/W6766196973","https://openalex.org/W6767164110","https://openalex.org/W6769511080"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W3196421258","https://openalex.org/W2358668433","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2151749779","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Single-channel":[0],"speech":[1,67],"separation":[2,68],"has":[3],"recently":[4],"made":[5],"great":[6],"progress":[7],"thanks":[8],"to":[9],"learned":[10,40,78],"filterbanks":[11,19,43,47,61,94],"as":[12],"used":[13],"in":[14,104],"ConvTasNet.":[15,86],"In":[16,34],"parallel,":[17],"parameterized":[18,42,93],"have":[20],"been":[21],"proposed":[22,76],"for":[23,117],"speaker":[24],"recognition":[25],"where":[26],"only":[27],"center":[28],"frequencies":[29],"and":[30,41,48,55,95,100],"bandwidths":[31],"are":[32,102],"learned.":[33],"this":[35],"work,":[36],"we":[37,88,108],"extend":[38],"real-valued":[39,83],"into":[44],"complex-valued":[45,98],"analytic":[46,77],"define":[49],"a":[50,63],"set":[51],"of":[52,85,92],"corresponding":[53],"representations":[54,99],"masking":[56],"strategies.":[57],"We":[58],"evaluate":[59],"these":[60],"on":[62],"newly":[64],"released":[65],"noisy":[66],"dataset":[69],"(WHAM).":[70],"The":[71],"results":[72],"show":[73,96,109],"that":[74,97,110],"the":[75,82,90,111],"filterbank":[79,84],"consistently":[80],"outperforms":[81],"Also,":[87],"validate":[89],"use":[91],"masks":[101],"beneficial":[103],"all":[105],"conditions.":[106],"Finally,":[107],"STFT":[112],"achieves":[113],"its":[114],"best":[115],"performance":[116],"2":[118],"ms":[119],"windows.":[120]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}