{"id":"https://openalex.org/W4283654390","doi":"https://doi.org/10.21437/interspeech.2022-680","title":"Confidence Score Based Conformer Speaker Adaptation for Speech Recognition","display_name":"Confidence Score Based Conformer Speaker Adaptation for Speech Recognition","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283654390","doi":"https://doi.org/10.21437/interspeech.2022-680"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-680","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-680","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":"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/A5106406454","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-8874-4167"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiajun DENG","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035857878","display_name":"Xurong Xie","orcid":"https://orcid.org/0000-0002-6714-6296"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xurong Xie","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407750","display_name":"Tianzi Wang","orcid":"https://orcid.org/0009-0005-5823-3039"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianzi Wang","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065896539","display_name":"Mingyu Cui","orcid":"https://orcid.org/0000-0001-9781-9407"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyu Cui","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033502057","display_name":"Boyang Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyang Xue","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075023049","display_name":"Zengrui Jin","orcid":"https://orcid.org/0000-0002-2637-7880"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengrui Jin","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003895235","display_name":"Mengzhe Geng","orcid":"https://orcid.org/0000-0002-7886-439X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengzhe Geng","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042515126","display_name":"Guinan Li","orcid":"https://orcid.org/0000-0002-2206-0237"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guinan Li","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5106406454"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":1.1446,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79653073,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2623","last_page":"2627"},"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":0.9994999766349792,"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":0.9925000071525574,"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/speech-recognition","display_name":"Speech recognition","score":0.7585004568099976},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6786749362945557},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6044522523880005},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5971769094467163},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4088554382324219},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3619213104248047},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32794633507728577},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12457561492919922}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7585004568099976},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6786749362945557},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6044522523880005},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5971769094467163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4088554382324219},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3619213104248047},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32794633507728577},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12457561492919922},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-680","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-680","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":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W82936479","https://openalex.org/W94829088","https://openalex.org/W173561343","https://openalex.org/W1513862252","https://openalex.org/W1526995323","https://openalex.org/W1892722218","https://openalex.org/W1985371235","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2090320273","https://openalex.org/W2094147890","https://openalex.org/W2106119541","https://openalex.org/W2128176022","https://openalex.org/W2139453310","https://openalex.org/W2166637769","https://openalex.org/W2239847623","https://openalex.org/W2276408190","https://openalex.org/W2280141299","https://openalex.org/W2394882406","https://openalex.org/W2401396087","https://openalex.org/W2407299475","https://openalex.org/W2531327146","https://openalex.org/W2542851870","https://openalex.org/W2567070169","https://openalex.org/W2594610113","https://openalex.org/W2936774411","https://openalex.org/W2939173691","https://openalex.org/W2962940707","https://openalex.org/W2972621414","https://openalex.org/W2972692349","https://openalex.org/W2972818416","https://openalex.org/W3007550212","https://openalex.org/W3097777922","https://openalex.org/W3097904285","https://openalex.org/W3113244915","https://openalex.org/W3161365423","https://openalex.org/W3161375121","https://openalex.org/W3163793923","https://openalex.org/W3194334755","https://openalex.org/W3198654230","https://openalex.org/W4287816637","https://openalex.org/W4287989389","https://openalex.org/W4302557958","https://openalex.org/W4402490925"],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W2249138175","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W3197877226"],"abstract_inverted_index":{"A":[0],"key":[1],"challenge":[2],"for":[3,41,176],"automatic":[4],"speech":[5],"recognition":[6],"(ASR)":[7],"systems":[8,134],"is":[9,55,74,98],"to":[10,28,51,76,93,137],"model":[11],"the":[12,63,78,107,113,126,154],"speaker":[13,19,31,39,68,94,128],"level":[14,95],"variability.In":[15],"this":[16],"paper,":[17],"compact":[18],"dependent":[20],"learning":[21],"hidden":[22],"unit":[23],"contributions":[24],"(LHUC)":[25],"are":[26],"used":[27,75,175],"facilitate":[29],"both":[30],"adaptive":[32],"training":[33],"(SAT)":[34],"and":[35,130,140,145,158,170],"test":[36,121],"time":[37,122],"unsupervised":[38,123],"adaptation":[40,50,124],"stateof-the-art":[42],"Conformer":[43,80,116,133],"based":[44,60,120],"end-to-end":[45],"ASR":[46],"systems.The":[47],"sensitivity":[48],"during":[49],"supervision":[52],"error":[53,149],"rate":[54,150],"reduced":[56],"using":[57,100],"confidence":[58,71,87,118],"score":[59,119],"selection":[61,97],"of":[62,67,103],"more":[64],"\"trustworthy\"":[65],"subset":[66],"specific":[69],"data.A":[70],"estimation":[72,102],"module":[73],"smooth":[77],"over-confident":[79],"decoder":[81],"output":[82],"probabilities":[83],"before":[84],"serving":[85],"as":[86],"scores.The":[88],"increased":[89],"data":[90,96],"sparsity":[91],"due":[92],"addressed":[99],"Bayesian":[101],"LHUC":[104],"parameters.Experiments":[105],"on":[106,153],"300-hour":[108],"Switchboard":[109],"corpus":[110],"suggest":[111],"that":[112],"proposed":[114],"LHUC-SAT":[115],"with":[117],"outperformed":[125],"baseline":[127],"independent":[129],"i-vector":[131],"adapted":[132],"by":[135],"up":[136],"1.0%,":[138,139],"1.2%":[141],"absolute":[142],"(9.0%,":[143],"7.9%,":[144],"8.9%":[146],"relative)":[147],"word":[148],"(WER)":[151],"reductions":[152],"NIST":[155],"Hub5'00,":[156],"RT02,":[157],"RT03":[159],"evaluation":[160],"sets":[161],"respectively.Consistent":[162],"performance":[163],"improvements":[164],"were":[165,174],"retained":[166],"after":[167],"external":[168],"Transformer":[169],"LSTM":[171],"language":[172],"models":[173],"rescoring.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}