{"id":"https://openalex.org/W4372270656","doi":"https://doi.org/10.1109/icassp49357.2023.10096763","title":"Guided Speech Enhancement Network","display_name":"Guided Speech Enhancement Network","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372270656","doi":"https://doi.org/10.1109/icassp49357.2023.10096763"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096763","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":"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/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"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":"Yang Yang","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028812926","display_name":"Shao-Fu Shih","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":"Shao-Fu Shih","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","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 LLC,U.S.A","Google LLC, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019362403","display_name":"Jamie Menjay Lin","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":"Jamie Menjay Lin","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073918065","display_name":"Chehung Lee","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":"Chehung Lee","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331862","display_name":"Yunpeng Li","orcid":"https://orcid.org/0000-0003-4798-541X"},"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":"Yunpeng Li","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083490412","display_name":"George Sung","orcid":"https://orcid.org/0000-0002-3146-6095"},"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":"George Sung","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091742738","display_name":"Matthias Grundmann","orcid":"https://orcid.org/0000-0002-1352-0625"},"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":"Matthias Grundmann","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google LLC,U.S.A","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google LLC, U.S.A","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":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9973999857902527,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9959999918937683,"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/speech-enhancement","display_name":"Speech enhancement","score":0.8867875337600708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.810293972492218},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7466706037521362},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6027100682258606},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5549371242523193},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5432475805282593},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5132551193237305},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4567062556743622},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3704885244369507},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2764758765697479},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12060844898223877}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8867875337600708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810293972492218},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7466706037521362},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6027100682258606},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5549371242523193},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5432475805282593},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5132551193237305},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4567062556743622},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3704885244369507},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2764758765697479},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12060844898223877},{"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/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096763","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096763","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1597121597","https://openalex.org/W2117678320","https://openalex.org/W2398042854","https://openalex.org/W2407685581","https://openalex.org/W2517616541","https://openalex.org/W2568308529","https://openalex.org/W2909607850","https://openalex.org/W2952218014","https://openalex.org/W2972782072","https://openalex.org/W2991361823","https://openalex.org/W2998572311","https://openalex.org/W3000389243","https://openalex.org/W3004309045","https://openalex.org/W3015372568","https://openalex.org/W3025581723","https://openalex.org/W3096408984","https://openalex.org/W3099330747","https://openalex.org/W3151596526","https://openalex.org/W3162341667","https://openalex.org/W3163243746","https://openalex.org/W3196940724","https://openalex.org/W3197260772","https://openalex.org/W3197334236","https://openalex.org/W4224133928","https://openalex.org/W4232282348","https://openalex.org/W4253006727","https://openalex.org/W4297841507","https://openalex.org/W6714030504","https://openalex.org/W6771763809","https://openalex.org/W6772349387","https://openalex.org/W6800489933"],"related_works":["https://openalex.org/W2170116036","https://openalex.org/W2149163000","https://openalex.org/W2418631473","https://openalex.org/W2161947961","https://openalex.org/W1488173215","https://openalex.org/W2163781980","https://openalex.org/W2149577017","https://openalex.org/W154138180","https://openalex.org/W4224919439","https://openalex.org/W2810291168"],"abstract_inverted_index":{"High":[0],"quality":[1],"speech":[2,27,35,54,69],"capture":[3,20],"has":[4],"been":[5],"widely":[6],"studied":[7],"for":[8,84,167,203],"both":[9,74],"voice":[10],"communication":[11],"and":[12,51,78,113,128,155,172,227],"human":[13],"computer":[14],"interface":[15],"reasons.":[16],"To":[17],"improve":[18],"the":[19,60,75,82,98,103,106,110,123,147,173,189,194,223],"performance,":[21],"we":[22,66],"can":[23,176],"often":[24,39],"find":[25],"multi-microphone":[26,218],"enhancement":[28,36,55,70],"techniques":[29],"deployed":[30],"on":[31,212,217],"various":[32],"devices.":[33],"Multi-microphone":[34],"problem":[37],"is":[38,184],"decomposed":[40],"into":[41],"two":[42,111],"decoupled":[43],"steps:":[44],"a":[45,52,68,90,159,168,180],"beamformer":[46,61,79,107,148],"that":[47,57,72,96],"provides":[48],"spatial":[49,119,137],"filtering":[50,138],"single-channel":[53],"model":[56,99,175],"cleans":[58],"up":[59],"output.":[62],"In":[63],"this":[64],"work,":[65],"propose":[67],"solution":[71,132,199],"takes":[73,133],"raw":[76],"microphone":[77,190],"outputs":[80],"as":[81,179,200],"input":[83],"an":[85],"ML":[86,195],"model.":[87],"We":[88,192,208],"devise":[89],"simple":[91],"yet":[92],"effective":[93],"training":[94],"scheme":[95],"allows":[97],"to":[100,164],"learn":[101],"from":[102,188],"cues":[104],"of":[105,126,135,141,162,222,225],"by":[108],"contrasting":[109],"inputs":[112],"greatly":[114],"boost":[115],"its":[116,210],"capability":[117],"in":[118,197,220],"rejection,":[120],"while":[121],"conducting":[122],"general":[124],"tasks":[125],"denoising":[127],"dereverberation.":[129],"The":[130],"proposed":[131],"advantage":[134],"classical":[136],"algorithms":[139],"instead":[140],"competing":[142],"with":[143],"them.":[144],"By":[145],"design,":[146],"module":[149,182,196],"then":[150],"could":[151],"be":[152,165,177],"selected":[153],"separately":[154],"does":[156],"not":[157],"require":[158],"large":[160],"amount":[161],"data":[163,215],"optimized":[166],"given":[169],"form":[170],"factor,":[171],"network":[174],"considered":[178],"standalone":[181],"which":[183],"highly":[185],"transferable":[186],"independently":[187],"array.":[191],"name":[193],"our":[198],"GSENet,":[201],"short":[202],"Guided":[204],"Speech":[205],"Enhancement":[206],"Network.":[207],"demonstrate":[209],"effectiveness":[211],"real":[213],"world":[214],"collected":[216],"devices":[219],"terms":[221],"suppression":[224],"noise":[226],"interfering":[228],"speech.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}