{"id":"https://openalex.org/W4372346118","doi":"https://doi.org/10.1109/icassp49357.2023.10096879","title":"AURA: Privacy-Preserving Augmentation to Improve Test Set Diversity in Speech Enhancement","display_name":"AURA: Privacy-Preserving Augmentation to Improve Test Set Diversity in Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346118","doi":"https://doi.org/10.1109/icassp49357.2023.10096879"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096879","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/A5029009552","display_name":"Xavier Gitiaux","orcid":"https://orcid.org/0000-0002-6648-0225"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xavier Gitiaux","raw_affiliation_strings":["Microsoft Corporation,Redmond,WA,USA","Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018926519","display_name":"Aditya Khant","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aditya Khant","raw_affiliation_strings":["Microsoft Corporation,Redmond,WA,USA","Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007693985","display_name":"Ebrahim Beyrami","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ebrahim Beyrami","raw_affiliation_strings":["Microsoft Corporation,Redmond,WA,USA","Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001022750","display_name":"Chandan K. Reddy","orcid":"https://orcid.org/0000-0003-2839-3662"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chandan Reddy","raw_affiliation_strings":["Microsoft Corporation,Redmond,WA,USA","Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020286799","display_name":"Jayant Gupchup","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayant Gupchup","raw_affiliation_strings":["Microsoft Corporation,Redmond,WA,USA","Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068040769","display_name":"Ross Cutler","orcid":"https://orcid.org/0000-0002-2004-3003"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ross Cutler","raw_affiliation_strings":["Microsoft Corporation,Redmond,WA,USA","Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1848,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.390182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.9983999729156494,"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":0.6801460981369019},{"id":"https://openalex.org/keywords/aura","display_name":"Aura","score":0.6193896532058716},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5609096884727478},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5572510361671448},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5141347050666809},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.47364509105682373},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4678742587566376},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4499828815460205},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4231805205345154},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.42220985889434814},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3524143695831299},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32474106550216675},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24574145674705505},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16909047961235046},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09667301177978516},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.09023767709732056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6801460981369019},{"id":"https://openalex.org/C2777350023","wikidata":"https://www.wikidata.org/wiki/Q1154226","display_name":"Aura","level":3,"score":0.6193896532058716},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5609096884727478},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5572510361671448},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5141347050666809},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.47364509105682373},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4678742587566376},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4499828815460205},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4231805205345154},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.42220985889434814},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3524143695831299},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32474106550216675},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24574145674705505},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16909047961235046},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09667301177978516},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.09023767709732056},{"id":"https://openalex.org/C2778541695","wikidata":"https://www.wikidata.org/wiki/Q133823","display_name":"Migraine","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"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/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096879","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096879","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1490682695","https://openalex.org/W1965546748","https://openalex.org/W2073459066","https://openalex.org/W2081580037","https://openalex.org/W2108598243","https://openalex.org/W2121973264","https://openalex.org/W2128470028","https://openalex.org/W2153342620","https://openalex.org/W2473418344","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2774918944","https://openalex.org/W2903158431","https://openalex.org/W2987274022","https://openalex.org/W3101275766","https://openalex.org/W3134428469","https://openalex.org/W3162616235","https://openalex.org/W3195156220","https://openalex.org/W3195288392","https://openalex.org/W3197042120","https://openalex.org/W3198130028","https://openalex.org/W3203083806","https://openalex.org/W4225302959","https://openalex.org/W4288083516","https://openalex.org/W6668990524","https://openalex.org/W6747231328","https://openalex.org/W6756615331","https://openalex.org/W6770636613","https://openalex.org/W6785110219","https://openalex.org/W6791519381","https://openalex.org/W6810523761"],"related_works":["https://openalex.org/W2105598729","https://openalex.org/W2503866489","https://openalex.org/W2028462208","https://openalex.org/W4285337533","https://openalex.org/W2982831492","https://openalex.org/W3138055416","https://openalex.org/W2187490799","https://openalex.org/W1574942924","https://openalex.org/W3094735304","https://openalex.org/W3019226033"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,52,99],"models":[2],"running":[3],"in":[4,117,132,159],"production":[5],"environments":[6],"are":[7,85],"commonly":[8],"trained":[9],"on":[10,25,71,87,96],"publicly":[11],"available":[12],"data.":[13,28],"This":[14,40],"approach":[15],"leads":[16],"to":[17,20,31,37,48,150,166,171],"regressions":[18],"due":[19,30],"the":[21],"lack":[22],"of":[23,77,119],"training/testing":[24],"representative":[26],"customer":[27,38],"Moreover,":[29,134,153],"privacy":[32],"reasons,":[33],"developers":[34],"cannot":[35],"listen":[36],"content.":[39],"\u2018ears-off\u2019":[41,67],"situation":[42],"motivates":[43],"Aura,":[44],"an":[45,111,126],"end-to-end":[46],"solution":[47],"make":[49],"existing":[50],"speech":[51,78,98],"train":[53],"and":[54,59,75,82,104,143],"test":[55,113,128],"sets":[56],"more":[57],"challenging":[58],"diverse":[60],"while":[61],"being":[62],"sample":[63],"efficient.":[64],"Aura":[65,95,109,135,154],"is":[66],"because":[68],"it":[69],"relies":[70],"a":[72,156],"feature":[73],"extractor":[74],"metrics":[76],"quality,":[79],"DNSMOS":[80],"P.835,":[81],"AECMOS,":[83],"that":[84],"pre-trained":[86],"data":[88],"obtained":[89],"from":[90],"public":[91],"sources.":[92],"We":[93],"evalaute":[94],"two":[97],"tasks:":[100],"noise":[101],"suppression":[102],"(NS)":[103],"audio":[105],"echo":[106],"cancellation":[107],"(AEC).":[108],"samples":[110],"NS":[112,141,174],"set":[114,129],"0.42":[115],"harder":[116,131],"terms":[118],"P.835":[120],"OVRL":[121],"than":[122],"random":[123,167],"sampling;":[124],"and,":[125],"AEC":[127,147],"1.93":[130],"AECMOS.":[133],"increases":[136],"diversity":[137],"by":[138,144],"30%":[139],"for":[140,146],"tasks":[142,148],"530%":[145],"compared":[149,165],"greedy":[151],"sampling.":[152],"achieves":[155],"26%":[157],"improvement":[158],"Spearman\u2019s":[160],"rank":[161,173],"correlation":[162],"coefficient":[163],"(SRCC)":[164],"sampling":[168],"when":[169],"used":[170],"stack":[172],"models.":[175]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}