{"id":"https://openalex.org/W4388593472","doi":"https://doi.org/10.1145/3625343.3625366","title":"Adaptive Speech Recognition via Dual-Level Sequential Pseudo Labels","display_name":"Adaptive Speech Recognition via Dual-Level Sequential Pseudo Labels","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4388593472","doi":"https://doi.org/10.1145/3625343.3625366"},"language":"en","primary_location":{"id":"doi:10.1145/3625343.3625366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3625343.3625366","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 Asia Conference on Artificial Intelligence, Machine Learning and Robotics","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/A5114949354","display_name":"Huizhou Liu","orcid":"https://orcid.org/0009-0003-9034-4236"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huizhou Liu","raw_affiliation_strings":["Hefei University of Technology, China and State Grid Anhui Electric Power Co., Ltd, China"],"raw_orcid":"https://orcid.org/0009-0003-9034-4236","affiliations":[{"raw_affiliation_string":"Hefei University of Technology, China and State Grid Anhui Electric Power Co., Ltd, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083246300","display_name":"Weihao Jiang","orcid":"https://orcid.org/0009-0006-8093-4437"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihao Jiang","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0009-0006-8093-4437","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055689719","display_name":"Junjie Huang","orcid":"https://orcid.org/0009-0009-2663-0848"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Huang","raw_affiliation_strings":["Zhejiang University, China"],"raw_orcid":"https://orcid.org/0009-0009-2663-0848","affiliations":[{"raw_affiliation_string":"Zhejiang University, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9966999888420105,"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/T10860","display_name":"Speech and Audio Processing","score":0.9952999949455261,"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":0.8206111192703247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6653986573219299},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5998642444610596},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5777007937431335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.513943612575531},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4629678726196289},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4430047571659088},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.41832512617111206},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40468642115592957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8206111192703247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6653986573219299},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5998642444610596},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5777007937431335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.513943612575531},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4629678726196289},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4430047571659088},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.41832512617111206},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40468642115592957},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3625343.3625366","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3625343.3625366","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 Asia Conference on Artificial Intelligence, Machine Learning and Robotics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2160306971","https://openalex.org/W2289394825","https://openalex.org/W2752782242","https://openalex.org/W2757519008","https://openalex.org/W2888954148","https://openalex.org/W2911629330","https://openalex.org/W2954996726","https://openalex.org/W2973133192","https://openalex.org/W3015537910","https://openalex.org/W3016010032","https://openalex.org/W3036601975","https://openalex.org/W3097287883","https://openalex.org/W3142589538","https://openalex.org/W3163464943","https://openalex.org/W3194701944","https://openalex.org/W4241087722","https://openalex.org/W4312365002","https://openalex.org/W4312897837"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W2997567050","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918"],"abstract_inverted_index":{"As":[0],"a":[1,91,167,173],"meaningful":[2],"task":[3],"of":[4,21,55,72,107,136],"speech":[5,8,28],"processing,":[6],"automatic":[7],"recognition":[9],"(ASR)":[10],"has":[11],"attracted":[12],"growing":[13],"interest":[14],"in":[15],"recent":[16],"years.":[17],"However,":[18],"traditional":[19],"methods":[20,110],"ASR":[22,188,203],"are":[23],"mainly":[24],"used":[25],"to":[26,36,50,67,132,153],"recognize":[27],"information":[29],"from":[30,44],"the":[31,37,41,53,56,69,77,104,114,120,124,134,142,148,155,160,178,186,190],"same":[32],"data":[33],"distribution.":[34],"Due":[35],"distribution":[38,46,79],"shift,":[39],"when":[40],"pre-trained":[42,74,116],"model":[43,57,117],"one":[45],"is":[47,65],"directly":[48],"applied":[49],"another":[51],"one,":[52],"performance":[54,199],"will":[58],"usually":[59],"deteriorate.":[60],"Therefore,":[61],"test-time":[62],"adaptation":[63,125],"(TTA)":[64],"proposed":[66],"improve":[68],"generalization":[70],"ability":[71],"source":[73,115],"models":[75,204],"on":[76,113,185],"target":[78,84],"by":[80],"only":[81],"using":[82],"unlabeled":[83],"data.":[85],"In":[86],"this":[87],"paper,":[88],"we":[89,127,140,171],"propose":[90,172],"novel":[92],"method":[93],"called":[94],"Dual-level":[95],"Sequential":[96],"Pseudo":[97],"labels":[98,106],"(DSP)":[99],"for":[100,177,200],"ASR.":[101],"Considering":[102],"that":[103,194],"pseudo":[105],"vanilla":[108],"TTA":[109],"heavily":[111],"rely":[112],"and":[118,150],"neglect":[119],"dynamic":[121],"knowledge":[122],"during":[123],"stage,":[126],"utilize":[128],"dual-level":[129],"average":[130],"predictions":[131],"enhance":[133],"accuracy":[135],"generated":[137],"labels.":[138],"Concretely,":[139],"adopt":[141],"teacher-student":[143],"learning":[144],"strategy":[145],"combined":[146],"with":[147],"weight-averaged":[149],"augmented-averaged":[151],"predition":[152],"reduce":[154],"error":[156],"accumulation.":[157],"Further,":[158],"since":[159],"text":[161],"generation":[162],"can":[163],"be":[164],"viewed":[165],"as":[166],"sequential":[168],"classification":[169],"task,":[170],"voting":[174],"threshold":[175],"mechanism":[176],"augmentation":[179],"process.":[180],"We":[181],"conduct":[182],"extensive":[183],"experiments":[184],"standard":[187],"datasets,":[189],"experimental":[191],"results":[192],"reveal":[193],"DSP":[195],"could":[196],"achieves":[197],"state-of-the-art":[198],"three":[201],"mainstream":[202],"under":[205],"various":[206],"domain":[207],"shifts.":[208]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}