{"id":"https://openalex.org/W4375868849","doi":"https://doi.org/10.1109/icassp49357.2023.10095961","title":"Multi-Channel Speaker Extraction with Adversarial Training: The Wavlab Submission to The Clarity ICASSP 2023 Grand Challenge","display_name":"Multi-Channel Speaker Extraction with Adversarial Training: The Wavlab Submission to The Clarity ICASSP 2023 Grand Challenge","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868849","doi":"https://doi.org/10.1109/icassp49357.2023.10095961"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/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"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["IT","US"],"is_corresponding":true,"raw_author_name":"Samuele Cornell","raw_affiliation_strings":["Università Politecnica delle Marche,Italy","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Università Politecnica delle Marche,Italy","institution_ids":["https://openalex.org/I122534668"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042385500","display_name":"Yoshiki Masuyama","orcid":"https://orcid.org/0000-0002-5881-0474"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Yoshiki Masuyama","raw_affiliation_strings":["Tokyo Metropolitan University,Japan","Carnegie Mellon University, USA","Tokyo Metropolitan University, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Japan","institution_ids":["https://openalex.org/I69740276"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA","Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061902495","display_name":"Manuel Pariente","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133941","display_name":"Applied Pulsed Power (United States)","ror":"https://ror.org/03m27ps35","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manuel Pariente","raw_affiliation_strings":["Pulse Audition,France","Pulse Audition, France"],"affiliations":[{"raw_affiliation_string":"Pulse Audition,France","institution_ids":["https://openalex.org/I4210133941"]},{"raw_affiliation_string":"Pulse Audition, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056281759","display_name":"Nobutaka Ono","orcid":"https://orcid.org/0000-0003-4242-2773"},"institutions":[{"id":"https://openalex.org/I69740276","display_name":"Tokyo Metropolitan University","ror":"https://ror.org/00ws30h19","country_code":"JP","type":"education","lineage":["https://openalex.org/I69740276"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ono","raw_affiliation_strings":["Tokyo Metropolitan University,Japan","Tokyo Metropolitan University, Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Metropolitan University,Japan","institution_ids":["https://openalex.org/I69740276"]},{"raw_affiliation_string":"Tokyo Metropolitan University, Japan","institution_ids":["https://openalex.org/I69740276"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034253968","display_name":"Stefano Squartini","orcid":"https://orcid.org/0000-0001-9374-0128"},"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":"Stefano Squartini","raw_affiliation_strings":["Università Politecnica delle Marche,Italy"],"affiliations":[{"raw_affiliation_string":"Università Politecnica delle Marche,Italy","institution_ids":["https://openalex.org/I122534668"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5047682990"],"corresponding_institution_ids":["https://openalex.org/I122534668","https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.2365,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88564812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"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":0.9983999729156494,"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":0.9940999746322632,"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":0.7675968408584595},{"id":"https://openalex.org/keywords/clarity","display_name":"CLARITY","score":0.7057402729988098},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6561174988746643},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6416210532188416},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5122711062431335},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.49531641602516174},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4616362750530243},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4504103660583496},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.449920117855072},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43574631214141846},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4295623302459717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4171193838119507},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28074461221694946},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10865405201911926},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09541907906532288}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7675968408584595},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.7057402729988098},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6561174988746643},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6416210532188416},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5122711062431335},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.49531641602516174},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4616362750530243},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4504103660583496},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.449920117855072},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43574631214141846},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4295623302459717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4171193838119507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28074461221694946},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10865405201911926},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09541907906532288},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.univpm.it:11566/325455","is_oa":false,"landing_page_url":"https://hdl.handle.net/11566/325455","pdf_url":null,"source":{"id":"https://openalex.org/S4306402571","display_name":"Universit\u00e0 Politecnica delle Marche (Universit\u00e0 Politecnica delle Marche)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122534668","host_organization_name":"Marche Polytechnic University","host_organization_lineage":["https://openalex.org/I122534668"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1582976041","https://openalex.org/W2021501756","https://openalex.org/W2760103357","https://openalex.org/W3032727804","https://openalex.org/W3171278394","https://openalex.org/W4225270933","https://openalex.org/W4225310539","https://openalex.org/W4307323391","https://openalex.org/W4311187069","https://openalex.org/W4321276703","https://openalex.org/W4372271367","https://openalex.org/W4385756463","https://openalex.org/W4394650347","https://openalex.org/W6779119091","https://openalex.org/W6810077993","https://openalex.org/W6842384739","https://openalex.org/W6846839833","https://openalex.org/W6850377926"],"related_works":["https://openalex.org/W3016163030","https://openalex.org/W4210341744","https://openalex.org/W2101293477","https://openalex.org/W1491017269","https://openalex.org/W2636483419","https://openalex.org/W2161947961","https://openalex.org/W4302766610","https://openalex.org/W2153327798","https://openalex.org/W4320085895","https://openalex.org/W2185164075"],"abstract_inverted_index":{"In":[0],"this":[1,91],"work":[2],"we":[3,104],"detail":[4],"our":[5,37,123,147,161],"submission":[6,39],"to":[7,18],"the":[8,41,63,74,80,110,117,142,152,158],"Clarity":[9,43],"ICASSP":[10],"2023":[11],"grand":[12],"challenge,":[13],"in":[14,30,50],"which":[15,48,68,103],"participants":[16],"have":[17],"develop":[19],"a":[20,71],"strong":[21],"target":[22,64],"speech":[23,88,129,136],"enhancement":[24,55],"system":[25,34],"for":[26,84],"hearing-aid":[27,128,135],"(HA)":[28],"devices":[29],"noisy-reverberant":[31],"environments.":[32],"Our":[33],"builds":[35],"on":[36,141,151,166,171],"previous":[38],"at":[40],"Second":[42],"Enhancement":[44],"Challenge":[45],"(CEC2):":[46],"iNeuBe-X,":[47],"consists":[49],"an":[51,59,77],"iterative":[52],"neural/conventional":[53],"beamforming":[54],"pipeline,":[56],"guided":[57],"by":[58,70,98],"enrollment":[60],"utterance":[61],"from":[62],"speaker.":[65],"This":[66,156],"model,":[67],"won":[69],"large":[72],"margin":[73],"CEC2,":[75],"is":[76,93,113],"extension":[78],"of":[79],"state-of-the-art":[81],"TF-GridNet":[82],"model":[83,125,148],"multi-channel,":[85],"streamable":[86],"target-speaker":[87],"enhancement.":[89],"Here,":[90],"approach":[92],"extended":[94],"and":[95,133,169],"further":[96],"improved":[97],"leveraging":[99],"generative":[100],"adversarial":[101],"training,":[102],"show":[105],"proves":[106],"especially":[107],"useful":[108],"when":[109],"training":[111,120],"data":[112],"limited.":[114],"Using":[115],"only":[116],"official":[118],"6k":[119],"scenes":[121],"data,":[122],"best":[124],"achieves":[126],"0.80":[127],"perception":[130],"index":[131,138],"(HASPI)":[132],"0.41":[134],"quality":[137],"(HASQI)":[139],"scores":[140],"synthetic":[143,173],"evaluation":[144,154,168],"set.":[145,155],"However,":[146],"generalized":[149],"poorly":[150],"semi-real":[153],"highlights":[157],"fact":[159],"that":[160],"community":[162],"should":[163],"focus":[164],"more":[165],"real-world":[167],"less":[170],"fully":[172],"datasets.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-02-07T06:11:34.122080","created_date":"2023-05-10T00:00:00"}