{"id":"https://openalex.org/W7148331912","doi":"https://doi.org/10.1109/asru65441.2025.11434810","title":"SUTA-LM: Bridging Test-Time Adaptation and Language Model Rescoring for Robust ASR","display_name":"SUTA-LM: Bridging Test-Time Adaptation and Language Model Rescoring for Robust ASR","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148331912","doi":"https://doi.org/10.1109/asru65441.2025.11434810"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132792870","display_name":"Wei-Ping Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Wei-Ping Huang","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108124525","display_name":"Guan-Ting Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Guan-Ting Lin","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132807525","display_name":"Hung-Yi Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Yi Lee","raw_affiliation_strings":["National Taiwan University,Graduate Institute of Communication Engineering,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University,Graduate Institute of Communication Engineering,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5132792870"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87553807,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.4131999909877777,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.4131999909877777,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.3790000081062317,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.025800000876188278,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/language-model","display_name":"Language model","score":0.8134999871253967},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.8101000189781189},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5629000067710876},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5194000005722046},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4984000027179718},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.49160000681877136},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4828999936580658},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4456000030040741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8435999751091003},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.8134999871253967},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8101000189781189},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5629000067710876},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4984000027179718},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.49160000681877136},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4828999936580658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4627000093460083},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.412200003862381},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37389999628067017},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3463999927043915},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.32440000772476196},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30300000309944153},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434810","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434810","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6359168887138367,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2559809918","https://openalex.org/W2799473636","https://openalex.org/W2888954148","https://openalex.org/W2973133192","https://openalex.org/W4221153728","https://openalex.org/W4312897837","https://openalex.org/W4385823503","https://openalex.org/W4391021731","https://openalex.org/W4391021773","https://openalex.org/W4402111726","https://openalex.org/W7133200675"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"progress":[1],"in":[2],"end-to-end":[3],"ASR,":[4],"real-world":[5],"domain":[6],"mismatches":[7],"still":[8],"cause":[9],"performance":[10],"drops,":[11],"which":[12],"Test-Time":[13],"Adaptation":[14],"(TTA)":[15],"aims":[16],"to":[17,115],"mitigate":[18],"by":[19,99,111],"adjusting":[20],"models":[21],"during":[22],"inference.":[23],"Recent":[24],"work":[25],"explores":[26],"combining":[27,65],"TTA":[28,52,85],"with":[29,55,87],"external":[30],"language":[31,56,88,112],"models,":[32],"using":[33],"techniques":[34],"like":[35],"beam":[36],"search":[37],"rescoring":[38,114],"or":[39],"generative":[40],"error":[41],"correction.":[42],"In":[43],"this":[44,71],"work,":[45],"we":[46,73],"identify":[47],"a":[48,76,94,132],"previously":[49],"overlooked":[50],"challenge:":[51],"can":[53],"interfere":[54],"model":[57,89,113],"rescoring,":[58],"revealing":[59],"the":[60,66,117],"nontrivial":[61],"nature":[62],"of":[63,81,135],"effectively":[64],"two":[67],"methods.":[68],"Based":[69],"on":[70,120],"insight,":[72],"propose":[74],"SUTA-LM,":[75],"simple":[77],"yet":[78],"effective":[79],"extension":[80],"SUTA,":[82],"an":[83,100],"entropy-minimization-based":[84],"approach,":[86],"rescoring.":[90],"SUTALM":[91],"first":[92],"applies":[93],"controlled":[95],"adaptation":[96],"process":[97],"guided":[98],"auto-step":[101],"selection":[102],"mechanism":[103],"leveraging":[104],"both":[105],"acoustic":[106],"and":[107],"linguistic":[108],"information,":[109],"followed":[110],"refine":[116],"outputs.":[118],"Experiments":[119],"18":[121],"diverse":[122],"ASR":[123],"datasets":[124],"show":[125],"that":[126],"SUTA-LM":[127],"achieves":[128],"robust":[129],"results":[130],"across":[131],"wide":[133],"range":[134],"domains.<sup":[136],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[137,139],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup><sup":[138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>The":[140],"source":[141],"code":[142],"is":[143],"available":[144],"at":[145],"https://github.com/hhhaaahhhaa/ASR-TTA":[146]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}