{"id":"https://openalex.org/W4319862412","doi":"https://doi.org/10.1109/slt54892.2023.10022892","title":"Learning Invariant Representation and Risk Minimized for Unsupervised Accent Domain Adaptation","display_name":"Learning Invariant Representation and Risk Minimized for Unsupervised Accent Domain Adaptation","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862412","doi":"https://doi.org/10.1109/slt54892.2023.10022892"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022892","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022892","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5068186778","display_name":"Chendong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chendong Zhao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Ping An Technology (Shenzhen) Co., Ltd., China","The Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"The Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Ping An Technology (Shenzhen) Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100940847","display_name":"Xiaoyang Qu","orcid":"https://orcid.org/0009-0009-6311-4332"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyang Qu","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Ping An Technology (Shenzhen) Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028229824","display_name":"Haoqian Wang","orcid":"https://orcid.org/0000-0003-2792-8469"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqian Wang","raw_affiliation_strings":["The Shenzhen International Graduate School, Tsinghua University,China","The Shenzhen International Graduate School, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Shenzhen International Graduate School, Tsinghua University,China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I4210114105"]},{"raw_affiliation_string":"The Shenzhen International Graduate School, Tsinghua University, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd.,China","Ping An Technology (Shenzhen) Co., Ltd., China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd.,China","institution_ids":["https://openalex.org/I4401726822"]},{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd., China","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2172,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.37516438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"33","issue":null,"first_page":"509","last_page":"516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9976000189781189,"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":0.7449166774749756},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6203242540359497},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6003304719924927},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5911012291908264},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5711544752120972},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5646991729736328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5607063174247742},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5471346974372864},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5098952054977417},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.498462438583374},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.44416308403015137},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3537096381187439},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.13684579730033875},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11324235796928406},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08442425727844238}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7449166774749756},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6203242540359497},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6003304719924927},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5911012291908264},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5711544752120972},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5646991729736328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5607063174247742},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5471346974372864},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5098952054977417},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.498462438583374},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.44416308403015137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3537096381187439},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.13684579730033875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11324235796928406},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08442425727844238},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022892","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022892","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3451530047","display_name":null,"funder_award_id":"2021B0101400003","funder_id":"https://openalex.org/F4320336405","funder_display_name":"Special Project for Research and Development in Key areas of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320336405","display_name":"Special Project for Research and Development in Key areas of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W108866686","https://openalex.org/W267812377","https://openalex.org/W1494198834","https://openalex.org/W1635512741","https://openalex.org/W2187089797","https://openalex.org/W2347098582","https://openalex.org/W2560674852","https://openalex.org/W2603276336","https://openalex.org/W2612690371","https://openalex.org/W2747329762","https://openalex.org/W2747874407","https://openalex.org/W2889494795","https://openalex.org/W2933138175","https://openalex.org/W2953190524","https://openalex.org/W2962850167","https://openalex.org/W2973049979","https://openalex.org/W2982223350","https://openalex.org/W3015213852","https://openalex.org/W3033038061","https://openalex.org/W3044481399","https://openalex.org/W3112702554","https://openalex.org/W3157503981","https://openalex.org/W3160366495","https://openalex.org/W3161223924","https://openalex.org/W3161411634","https://openalex.org/W3162812479","https://openalex.org/W3163464943","https://openalex.org/W3196787717","https://openalex.org/W3209059054","https://openalex.org/W4212774754","https://openalex.org/W4221160950","https://openalex.org/W4319586927","https://openalex.org/W6603838645","https://openalex.org/W6609836551","https://openalex.org/W6745117592","https://openalex.org/W6753579488","https://openalex.org/W6769196770","https://openalex.org/W6771467084","https://openalex.org/W6780218876","https://openalex.org/W6788335241","https://openalex.org/W6795952400"],"related_works":["https://openalex.org/W3174759195","https://openalex.org/W3167013339","https://openalex.org/W4287121366","https://openalex.org/W60493759","https://openalex.org/W4386437125","https://openalex.org/W4308619659","https://openalex.org/W3213069564","https://openalex.org/W2147093486","https://openalex.org/W2997229301","https://openalex.org/W2785325870"],"abstract_inverted_index":{"Unsupervised":[0],"representation":[1],"learning":[2,74],"for":[3,9,48,51],"speech":[4,10,16,82],"audios":[5],"attained":[6],"impressive":[7],"performances":[8],"recognition":[11],"tasks,":[12],"particularly":[13],"when":[14],"annotated":[15],"is":[17,30,39],"limited.":[18],"However,":[19],"the":[20,43,54,58,93,99,108,112],"unsupervised":[21],"paradigm":[22],"needs":[23,65],"to":[24,61,66,84],"be":[25,67],"carefully":[26],"designed":[27],"and":[28],"little":[29],"known":[31],"about":[32],"what":[33],"properties":[34],"these":[35],"representations":[36,47,60,76,83],"acquire.":[37],"There":[38],"no":[40],"guarantee":[41],"that":[42,92],"model":[44],"learns":[45],"meaningful":[46],"valuable":[49],"information":[50],"recognition.":[52],"Moreover,":[53],"adaptation":[55,109],"ability":[56],"of":[57,81,102],"learned":[59,94],"other":[62],"domains":[63],"still":[64],"estimated.":[68],"In":[69],"this":[70],"work,":[71],"we":[72],"explore":[73],"domain-invariant":[75],"via":[77],"a":[78],"direct":[79],"mapping":[80],"their":[85],"corresponding":[86],"high-level":[87],"linguistic":[88],"informations.":[89],"Results":[90],"prove":[91],"latents":[95],"not":[96],"only":[97],"capture":[98],"articulatory":[100],"feature":[101],"each":[103],"phoneme":[104],"but":[105],"also":[106],"enhance":[107],"ability,":[110],"outperforming":[111],"baseline":[113],"largely":[114],"on":[115],"accented":[116],"benchmarks.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}