{"id":"https://openalex.org/W4297841645","doi":"https://doi.org/10.21437/interspeech.2022-10484","title":"End-to-end speech recognition modeling from de-identified data","display_name":"End-to-end speech recognition modeling from de-identified data","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841645","doi":"https://doi.org/10.21437/interspeech.2022-10484"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10484","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10484","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5077262177","display_name":"M. Flechl","orcid":"https://orcid.org/0000-0003-4750-3548"},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Martin Flechl","raw_affiliation_strings":["Nuance Communications Inc., Burlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc., Burlington, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040098877","display_name":"Shouchun Yin","orcid":"https://orcid.org/0000-0003-1086-1755"},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shou-Chun Yin","raw_affiliation_strings":["Nuance Communications Inc., Burlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc., Burlington, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667214","display_name":"Junho Park","orcid":"https://orcid.org/0009-0002-5421-594X"},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junho Park","raw_affiliation_strings":["Nuance Communications Inc., Burlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc., Burlington, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010304632","display_name":"Peter Skala","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Skala","raw_affiliation_strings":["Nuance Communications Inc., Burlington, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc., Burlington, USA","institution_ids":["https://openalex.org/I4210125787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5077262177"],"corresponding_institution_ids":["https://openalex.org/I4210125787"],"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":"1382","last_page":"1386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9424999952316284,"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":0.9424999952316284,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7475682497024536},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7417682409286499},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6893332004547119},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4155900776386261},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36083298921585083},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1479145586490631}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7475682497024536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7417682409286499},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6893332004547119},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4155900776386261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36083298921585083},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1479145586490631}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10484","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10484","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1855892484","https://openalex.org/W2010365091","https://openalex.org/W2015620729","https://openalex.org/W2895223087","https://openalex.org/W2936774411","https://openalex.org/W2963250244","https://openalex.org/W2963300588","https://openalex.org/W2963362078","https://openalex.org/W2963956191","https://openalex.org/W2964243274","https://openalex.org/W2973127116","https://openalex.org/W3016010032","https://openalex.org/W3021066808","https://openalex.org/W3048384720","https://openalex.org/W3092028330","https://openalex.org/W3097777922","https://openalex.org/W3196889659","https://openalex.org/W4283324956","https://openalex.org/W4287121924","https://openalex.org/W4287198862","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2778699561","https://openalex.org/W2971982237","https://openalex.org/W2938947737","https://openalex.org/W2312526371","https://openalex.org/W2954695182","https://openalex.org/W4224917401","https://openalex.org/W4303519918","https://openalex.org/W2600628583","https://openalex.org/W2771275309","https://openalex.org/W3197777440"],"abstract_inverted_index":{"De-identification":[0],"of":[1,44,77,119,125,132,156,163,173],"data":[2,32,108,124],"used":[3,112],"for":[4,41,59],"automatic":[5],"speech":[6],"recognition":[7,43,162],"modeling":[8],"is":[9,65,70,83,153],"a":[10,35,56,73,130,147],"critical":[11],"component":[12],"in":[13,17,39,138,160],"protecting":[14],"privacy,":[15],"especially":[16],"the":[18,42,78,96,106,117,134,139,154,161,167,174],"medical":[19,126],"domain.However,":[20],"simply":[21],"removing":[22],"all":[23],"personally":[24],"identifiable":[25],"information":[26],"(PII)":[27],"from":[28,50,95,105],"end-to-end":[29],"model":[30],"training":[31],"leads":[33],"to":[34,113],"significant":[36],"performance":[37,118,136,175],"degradation":[38,137,176],"particular":[40],"names,":[45],"dates,":[46],"locations,":[47],"and":[48,54,67,128,158],"words":[49],"similar":[51],"categories.We":[52],"propose":[53],"evaluate":[55,116],"two-step":[57],"method":[58,121],"partially":[60],"recovering":[61],"this":[62,120],"loss.First,":[63],"PII":[64,168],"identified,":[66],"each":[68],"occurrence":[69],"replaced":[71],"with":[72,102],"random":[74],"word":[75,141],"sequence":[76],"same":[79],"category.Then,":[80],"corresponding":[81],"audio":[82,92],"produced":[84],"via":[85],"text-to-speech":[86],"or":[87],"by":[88],"splicing":[89],"together":[90,101],"matching":[91],"fragments":[93],"extracted":[94],"corpus.These":[97],"artificial":[98],"audio/label":[99],"pairs,":[100],"speaker":[103],"turns":[104],"original":[107],"without":[109],"PII,":[110],"are":[111],"train":[114],"models.We":[115],"on":[122,166],"in-house":[123],"conversations":[127],"observe":[129],"recovery":[131],"almost":[133],"entire":[135],"general":[140],"error":[142],"rate":[143],"while":[144],"still":[145],"maintaining":[146],"strong":[148],"diarization":[149],"performance.Our":[150],"main":[151],"focus":[152],"improvement":[155],"recall":[157],"precision":[159],"PII-related":[164],"words.Depending":[165],"category,":[169],"between":[170],"50%":[171],"-90%":[172],"can":[177],"be":[178],"recovered":[179],"using":[180],"our":[181],"proposed":[182],"method.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}