{"id":"https://openalex.org/W4391021763","doi":"https://doi.org/10.1109/asru57964.2023.10389682","title":"Efficient Text-Only Domain Adaptation For CTC-Based ASR","display_name":"Efficient Text-Only Domain Adaptation For CTC-Based ASR","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021763","doi":"https://doi.org/10.1109/asru57964.2023.10389682"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5100734451","display_name":"Chang Chen","orcid":"https://orcid.org/0000-0001-8281-9244"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Chen","raw_affiliation_strings":["AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086338661","display_name":"Xun Gong","orcid":"https://orcid.org/0000-0002-3364-8407"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xun Gong","raw_affiliation_strings":["AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai,China","Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Institute Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, MoE Key Lab of Artificial Intelligence, AI Institute Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9916999936103821,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9889000058174133,"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/computer-science","display_name":"Computer science","score":0.7005840539932251},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6679836511611938},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6494370698928833},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5481978058815002},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5462008714675903},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5190528035163879},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5172615647315979},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49845075607299805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41555464267730713},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14855638146400452},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11761060357093811}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7005840539932251},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6679836511611938},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6494370698928833},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5481978058815002},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5462008714675903},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5190528035163879},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5172615647315979},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49845075607299805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41555464267730713},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14855638146400452},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11761060357093811},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W46679369","https://openalex.org/W108866686","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W2024490156","https://openalex.org/W2160306971","https://openalex.org/W2327501763","https://openalex.org/W2795867901","https://openalex.org/W2892009249","https://openalex.org/W2911629330","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963240019","https://openalex.org/W3096122506","https://openalex.org/W3097777922","https://openalex.org/W3162249256","https://openalex.org/W3193461931","https://openalex.org/W3197242296","https://openalex.org/W3198694222","https://openalex.org/W3202419788","https://openalex.org/W4292387508","https://openalex.org/W4297841852","https://openalex.org/W4372346361","https://openalex.org/W4385245566","https://openalex.org/W6601894380","https://openalex.org/W6638749077","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W350032239","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W4394775207"],"abstract_inverted_index":{"For":[0],"connectionist":[1],"temporal":[2],"classification":[3],"(CTC)":[4],"based":[5],"speech":[6],"recognition":[7],"(ASR)":[8],"models,":[9],"text-only":[10,24],"domain":[11,25,76],"adaptation":[12,26,61],"still":[13],"faces":[14],"several":[15],"challenges.":[16],"In":[17],"this":[18],"study,":[19],"we":[20],"propose":[21],"an":[22],"efficient":[23],"method":[27,99],"for":[28,129],"CTC-based":[29],"models.":[30],"We":[31],"introduce":[32],"the":[33,46,50,54,57,60,66,70,74,85,97,110,138],"assistant":[34],"textual":[35,40],"adapter":[36],"(ATA)":[37],"to":[38,119,137],"learn":[39],"features":[41],"and":[42,115,141],"transform":[43],"them":[44],"into":[45],"latent":[47],"space":[48],"of":[49,56,69],"acoustic":[51,71],"encoder.":[52],"With":[53],"help":[55],"ATA":[58],"module,":[59],"is":[62],"achieved":[63],"by":[64,84],"fine-tuning":[65],"top":[67],"layers":[68],"encoder":[72],"with":[73,87,109,148],"target":[75,132],"text.":[77],"Meanwhile,":[78],"further":[79],"improvement":[80],"can":[81,100],"be":[82],"obtained":[83],"integration":[86],"shallow":[88],"fusion":[89],"(SF).":[90],"Adapted":[91],"from":[92],"LibriSpeech,":[93],"experiments":[94],"show":[95],"that":[96],"proposed":[98],"achieve":[101],"averaged":[102],"29.7%":[103],"relative":[104],"WER":[105],"reduction":[106],"(WERR)":[107],"compared":[108,118,136,147],"un-adapted":[111,139],"baseline":[112],"on":[113,145],"WSJ,":[114],"10.5%":[116],"WERR":[117,128,144],"SF":[120],"as":[121],"well.":[122],"Moreover,":[123],"it":[124],"also":[125,142],"shows":[126],"15.4\u223c37.1%":[127],"10":[130],"GigaSpeech":[131],"domains":[133],"test":[134],"sets":[135],"baseline,":[140],"6.5%":[143],"average":[146],"SF.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}