{"id":"https://openalex.org/W4372270707","doi":"https://doi.org/10.1109/icassp49357.2023.10096836","title":"Improving Fairness and Robustness in End-to-End Speech Recognition Through Unsupervised Clustering","display_name":"Improving Fairness and Robustness in End-to-End Speech Recognition Through Unsupervised Clustering","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372270707","doi":"https://doi.org/10.1109/icassp49357.2023.10096836"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096836","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/A5000659085","display_name":"Irina-Elena Veliche","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irina-Elena Veliche","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019636504","display_name":"Pascale Fung","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pascale Fung","raw_affiliation_strings":["Meta AI,USA","Meta AI, USA","The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI,USA","institution_ids":[]},{"raw_affiliation_string":"Meta AI, USA","institution_ids":[]},{"raw_affiliation_string":"The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9918000102043152,"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/T11309","display_name":"Music and Audio Processing","score":0.9829999804496765,"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/robustness","display_name":"Robustness (evolution)","score":0.8366191387176514},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7787638306617737},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7752808332443237},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6610490083694458},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6275888681411743},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.615565299987793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.411205530166626},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.10950231552124023}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8366191387176514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787638306617737},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7752808332443237},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6610490083694458},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6275888681411743},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.615565299987793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.411205530166626},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10950231552124023},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/icassp49357.2023.10096836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096836","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:repository.hkust.edu.hk:1783.1-135571","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-135571","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1941659294","https://openalex.org/W1970329478","https://openalex.org/W2137354628","https://openalex.org/W2141656153","https://openalex.org/W2142402086","https://openalex.org/W2143693287","https://openalex.org/W2150593711","https://openalex.org/W2338318698","https://openalex.org/W2949488362","https://openalex.org/W2962893195","https://openalex.org/W3012624518","https://openalex.org/W3015194534","https://openalex.org/W3024869864","https://openalex.org/W3147107444","https://openalex.org/W3162665866","https://openalex.org/W3215236363","https://openalex.org/W3217246256","https://openalex.org/W4286902103","https://openalex.org/W4296069263","https://openalex.org/W6793191273","https://openalex.org/W6802818367"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2562096895","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W4307784074"],"abstract_inverted_index":{"The":[0],"challenge":[1],"of":[2,19,89,138],"fairness":[3,59,86],"arises":[4],"when":[5],"Automatic":[6],"Speech":[7],"Recognition":[8],"(ASR)":[9],"systems":[10,53],"do":[11,54],"not":[12,55],"perform":[13,56],"equally":[14],"well":[15],"for":[16,47,51,151,158],"all":[17,48,152],"sub-groups":[18],"the":[20,23],"population.":[21],"In":[22,75],"past":[24],"few":[25],"years":[26],"there":[27],"have":[28],"been":[29],"many":[30],"improvements":[31,150],"in":[32,72,104,125,156],"overall":[33],"speech":[34],"recognition":[35],"quality,":[36],"but":[37],"without":[38,92],"any":[39],"particular":[40,157],"focus":[41],"on":[42,117],"advancing":[43],"Equality":[44],"and":[45,87,155],"Equity":[46],"user":[49],"groups":[50,154],"whom":[52],"well.":[57],"ASR":[58,91],"is":[60],"therefore":[61],"also":[62,69],"a":[63,80,112,118],"robustness":[64,88],"issue.":[65],"Meanwhile,":[66],"data":[67],"privacy":[68,81],"takes":[70],"priority":[71],"production":[73],"systems.":[74],"this":[76],"paper,":[77],"we":[78,122],"present":[79],"preserving":[82],"approach":[83],"to":[84,129],"improve":[85],"end-to-end":[90],"using":[93,111],"metadata,":[94],"zip":[95],"codes,":[96],"or":[97,100],"even":[98],"speaker":[99,113,139],"utterance":[101,108,140],"embeddings":[102,110,141],"directly":[103],"training.":[105],"We":[106,133],"extract":[107],"level":[109],"ID":[114],"model":[115,146],"trained":[116],"public":[119],"dataset,":[120],"which":[121,148],"then":[123],"use":[124,134],"an":[126],"unsupervised":[127],"fashion":[128],"create":[130],"acoustic":[131],"clusters.":[132],"cluster":[135],"IDs":[136],"instead":[137],"as":[142],"extra":[143],"features":[144],"during":[145],"training,":[147],"shows":[149],"demographic":[153],"different":[159],"accents.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}