{"id":"https://openalex.org/W4312822757","doi":"https://doi.org/10.1109/iwaenc53105.2022.9914731","title":"Streaming Noise Context Aware Enhancement for Automatic Speech Recognition in Multi-Talker Environments","display_name":"Streaming Noise Context Aware Enhancement for Automatic Speech Recognition in Multi-Talker Environments","publication_year":2022,"publication_date":"2022-09-05","ids":{"openalex":"https://openalex.org/W4312822757","doi":"https://doi.org/10.1109/iwaenc53105.2022.9914731"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc53105.2022.9914731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc53105.2022.9914731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5084871195","display_name":"Joe Caroselli","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":"Joe Caroselli","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":"last","author":{"id":"https://openalex.org/A5102111886","display_name":"Yiteng Huang","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":"Yiteng Huang","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":3,"corresponding_author_ids":["https://openalex.org/A5084871195"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1580145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8257179260253906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.779007077217102},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7456763982772827},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6251659393310547},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5390287041664124},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5211982131004333},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5210354328155518},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47982287406921387},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4697166979312897},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.41935813426971436},{"id":"https://openalex.org/keywords/artificial-noise","display_name":"Artificial noise","score":0.4180343747138977},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.41635602712631226},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3774046301841736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2757123112678528},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1512882113456726},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07098683714866638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8257179260253906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.779007077217102},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7456763982772827},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6251659393310547},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5390287041664124},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5211982131004333},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5210354328155518},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47982287406921387},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4697166979312897},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.41935813426971436},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.4180343747138977},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.41635602712631226},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3774046301841736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2757123112678528},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1512882113456726},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07098683714866638},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C47798520","wikidata":"https://www.wikidata.org/wiki/Q190157","display_name":"Transmitter","level":3,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwaenc53105.2022.9914731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc53105.2022.9914731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2144244295","https://openalex.org/W2168729028","https://openalex.org/W2221409856","https://openalex.org/W2398042854","https://openalex.org/W2400339399","https://openalex.org/W2473329891","https://openalex.org/W2506203739","https://openalex.org/W2559809918","https://openalex.org/W2586584460","https://openalex.org/W2617258110","https://openalex.org/W2627092829","https://openalex.org/W2748545504","https://openalex.org/W2750499125","https://openalex.org/W2884797218","https://openalex.org/W2889013998","https://openalex.org/W2891997645","https://openalex.org/W2936774411","https://openalex.org/W2937769560","https://openalex.org/W2952218014","https://openalex.org/W2963122170","https://openalex.org/W2963827914","https://openalex.org/W2972402291","https://openalex.org/W2972992051","https://openalex.org/W2973062255","https://openalex.org/W3008762051","https://openalex.org/W3015194534","https://openalex.org/W3015199127","https://openalex.org/W3015834770","https://openalex.org/W3099330747","https://openalex.org/W3160766462","https://openalex.org/W6755462816","https://openalex.org/W6790217613"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2401089611","https://openalex.org/W2373767407","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W4252682934","https://openalex.org/W2851491717","https://openalex.org/W2072884270","https://openalex.org/W2002243964","https://openalex.org/W2022538999"],"abstract_inverted_index":{"One":[0],"of":[1,179],"the":[2,15,71,76,79,86,91,97,108,127,134,140,169],"most":[3],"challenging":[4],"scenarios":[5],"for":[6],"smart":[7,29],"speakers":[8],"is":[9,18,82,90,113,131],"multi-talker,":[10],"when":[11],"target":[12,107],"speech":[13,22,58],"from":[14,23],"desired":[16,109],"speaker":[17],"mixed":[19],"with":[20],"interfering":[21],"one":[24,157],"or":[25],"more":[26],"speakers.":[27],"A":[28],"assistant":[30],"needs":[31,44],"to":[32,36,40,45,75,84,103,106,154,158],"determine":[33,104],"which":[34,39,81,95,122,145,156],"voice":[35],"recognize":[37],"and":[38,42,100,184],"ignore":[41],"it":[43],"do":[46],"so":[47],"in":[48,139],"a":[49,124,173],"streaming,":[50],"low-latency":[51],"manner.":[52],"This":[53],"work":[54,147],"presents":[55],"two":[56,135],"multi-microphone":[57],"enhancement":[59],"algorithms":[60,136],"targeted":[61],"at":[62,181,186],"this":[63],"scenario.":[64],"Targeting":[65],"on-device":[66],"use-cases,":[67],"we":[68],"assume":[69],"that":[70,133],"algorithm":[72,118,153],"has":[73],"access":[74],"signal":[77],"before":[78],"hotword,":[80],"referred":[83],"as":[85],"noise":[87,98,116,128],"context.":[88,129],"First":[89],"Context":[92],"Aware":[93],"Beamformer":[94],"uses":[96],"context":[99],"detected":[101],"hotword":[102],"how":[105],"speaker.":[110],"The":[111],"second":[112],"an":[114,152],"adaptive":[115],"cancellation":[117],"called":[119],"Speech":[120],"Cleaner":[121],"trains":[123],"filter":[125],"using":[126,165],"It":[130],"demonstrated":[132],"are":[137],"complementary":[138],"signal-to-noise":[141],"ratio":[142],"conditions":[143],"under":[144],"they":[146],"well.":[148],"We":[149],"also":[150],"propose":[151],"select":[155],"use":[159],"based":[160],"on":[161],"estimated":[162],"SNR.":[163],"When":[164],"3":[166],"microphone":[167],"channels,":[168],"final":[170],"system":[171],"achieves":[172],"relative":[174],"word":[175],"error":[176],"rate":[177],"reduction":[178],"55%":[180],"-12":[182],"dB,":[183],"43%":[185],"12":[187],"dB.":[188]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}