{"id":"https://openalex.org/W4375869429","doi":"https://doi.org/10.1109/icassp49357.2023.10095369","title":"Conditional Conformer: Improving Speaker Modulation For Single And Multi-User Speech Enhancement","display_name":"Conditional Conformer: Improving Speaker Modulation For Single And Multi-User Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869429","doi":"https://doi.org/10.1109/icassp49357.2023.10095369"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095369","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/A5042631153","display_name":"Tom O\u2019Malley","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":true,"raw_author_name":"Tom O\u2019Malley","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"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/A5058886181","display_name":"Shaojin Ding","orcid":"https://orcid.org/0000-0002-2108-3111"},"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":"Shaojin Ding","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"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/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"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":"Arun Narayanan","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"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/A5100418247","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0001-6913-8604"},"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":"Quan Wang","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"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/A5003481800","display_name":"Rajeev Rikhye","orcid":"https://orcid.org/0000-0003-2011-2897"},"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":"Rajeev Rikhye","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"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/A5026297587","display_name":"Qiao Liang","orcid":"https://orcid.org/0000-0003-4464-4644"},"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":"Qiao Liang","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"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/A5101319167","display_name":"Yanzhang He","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":"Yanzhang He","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"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/A5048236120","display_name":"Ian McGraw","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":"Ian McGraw","raw_affiliation_strings":["Google LLC,U.S.A","Google LLC, U.S.A"],"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":8,"corresponding_author_ids":["https://openalex.org/A5042631153"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.6113,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63574335,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9937999844551086,"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":0.7430410981178284},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6987951397895813},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5744831562042236},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5739932656288147},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5739316940307617},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5516560673713684},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.47185537219047546},{"id":"https://openalex.org/keywords/modulation","display_name":"Modulation (music)","score":0.4448874294757843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3785160779953003},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32527393102645874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12104851007461548},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11190852522850037},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09249436855316162}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430410981178284},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6987951397895813},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5744831562042236},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5739932656288147},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5739316940307617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5516560673713684},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.47185537219047546},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.4448874294757843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3785160779953003},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32527393102645874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12104851007461548},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11190852522850037},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09249436855316162},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095369","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":0.6000000238418579,"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":48,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1597121597","https://openalex.org/W2141411743","https://openalex.org/W2473329891","https://openalex.org/W2559809918","https://openalex.org/W2617258110","https://openalex.org/W2627092829","https://openalex.org/W2748545504","https://openalex.org/W2750499125","https://openalex.org/W2760103357","https://openalex.org/W2884797218","https://openalex.org/W2889013998","https://openalex.org/W2897924318","https://openalex.org/W2928941594","https://openalex.org/W2936774411","https://openalex.org/W2948981900","https://openalex.org/W2953384591","https://openalex.org/W2962788625","https://openalex.org/W2963122170","https://openalex.org/W2963431393","https://openalex.org/W2963574857","https://openalex.org/W2963727135","https://openalex.org/W2963827914","https://openalex.org/W2973062255","https://openalex.org/W3015746570","https://openalex.org/W3096090308","https://openalex.org/W3097777922","https://openalex.org/W3160766462","https://openalex.org/W3162847598","https://openalex.org/W3163842642","https://openalex.org/W3179294409","https://openalex.org/W4223655162","https://openalex.org/W4225873749","https://openalex.org/W4226428303","https://openalex.org/W4283069943","https://openalex.org/W4297841507","https://openalex.org/W4319862721","https://openalex.org/W4320930577","https://openalex.org/W6629717138","https://openalex.org/W6713134421","https://openalex.org/W6741807409","https://openalex.org/W6743440867","https://openalex.org/W6746023985","https://openalex.org/W6760633627","https://openalex.org/W6763608318","https://openalex.org/W6782142667","https://openalex.org/W6786197189","https://openalex.org/W6849319285"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"Recently,":[0],"Feature-wise":[1],"Linear":[2],"Modulation":[3],"(FiLM)":[4],"has":[5],"been":[6],"shown":[7],"to":[8,12,54,73,85,143],"outperform":[9],"other":[10],"approaches":[11],"incorporate":[13],"speaker":[14,44,95,112],"embedding":[15],"into":[16,31,114],"speech":[17,38],"separation":[18],"and":[19,41,64,134],"VoiceFilter":[20,87,132],"models.":[21],"We":[22,47,118],"propose":[23],"an":[24,144],"improved":[25],"method":[26],"of":[27,93],"incorporating":[28],"such":[29],"embeddings":[30,96,113],"a":[32,56,98,115],"Voice-":[33],"Filter":[34],"frontend":[35],"for":[36],"automatic":[37],"recognition":[39],"(ASR)":[40],"text-":[42],"independent":[43],"verification":[45],"(TI-SV).":[46],"extend":[48],"the":[49,66,94,111],"widely-":[50],"used":[51],"Conformer":[52,116],"architecture":[53],"construct":[55],"FiLM":[57,67],"Block":[58],"with":[59],"additional":[60],"feature":[61],"processing":[62],"before":[63],"after":[65],"layers.":[68],"Apart":[69],"from":[70],"its":[71],"application":[72],"single-user":[74],"VoiceFilter,":[75],"we":[76,105],"show":[77],"that":[78],"our":[79,135],"system":[80],"can":[81],"be":[82],"easily":[83],"extended":[84],"multi-user":[86,131],"models":[88],"via":[89],"element-wise":[90,136],"max":[91,137],"pooling":[92,138],"in":[97],"projected":[99],"space.":[100],"The":[101],"final":[102],"architecture,":[103],"which":[104],"call":[106],"Conditional":[107],"Conformer,":[108],"tightly":[109],"integrates":[110],"backbone.":[117],"improve":[119],"TI-SV":[120],"equal":[121],"error":[122],"rates":[123],"by":[124,147],"as":[125,127,148,150],"much":[126,149],"56%":[128],"over":[129],"prior":[130],"models,":[133],"reduces":[139],"relative":[140],"WER":[141],"compared":[142],"attention":[145],"mechanism":[146],"10%.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}