{"id":"https://openalex.org/W4319862680","doi":"https://doi.org/10.1109/slt54892.2023.10022825","title":"A Context-Aware Knowledge Transferring Strategy for CTC-Based ASR","display_name":"A Context-Aware Knowledge Transferring Strategy for CTC-Based ASR","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862680","doi":"https://doi.org/10.1109/slt54892.2023.10022825"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022825","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":"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/A5013041579","display_name":"Ke-Han Lu","orcid":"https://orcid.org/0000-0002-5331-0534"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ke-Han Lu","raw_affiliation_strings":["National Taiwan University of Science and Technology,Taiwan","National Taiwan University of Science and Technology, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology,Taiwan","institution_ids":["https://openalex.org/I154864474"]},{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100714445","display_name":"Kuan-Yu Chen","orcid":"https://orcid.org/0000-0001-9656-7551"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kuan-Yu Chen","raw_affiliation_strings":["National Taiwan University of Science and Technology,Taiwan","National Taiwan University of Science and Technology, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University of Science and Technology,Taiwan","institution_ids":["https://openalex.org/I154864474"]},{"raw_affiliation_string":"National Taiwan University of Science and Technology, Taiwan","institution_ids":["https://openalex.org/I154864474"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013041579"],"corresponding_institution_ids":["https://openalex.org/I154864474"],"apc_list":null,"apc_paid":null,"fwci":1.2453,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.80322749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"60","last_page":"67"},"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":0.996399998664856,"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":0.9950000047683716,"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":0.8456857204437256},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6906711459159851},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.6851456165313721},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6685933470726013},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5843193531036377},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5400692820549011},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5274420380592346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.503072202205658},{"id":"https://openalex.org/keywords/conditional-independence","display_name":"Conditional independence","score":0.4915502965450287},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4722672700881958},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.45556142926216125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4473346173763275},{"id":"https://openalex.org/keywords/knowledge-acquisition","display_name":"Knowledge acquisition","score":0.4120883345603943},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4024602174758911},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27053141593933105},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0781843364238739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8456857204437256},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6906711459159851},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.6851456165313721},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6685933470726013},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5843193531036377},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5400692820549011},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5274420380592346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503072202205658},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.4915502965450287},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4722672700881958},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.45556142926216125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4473346173763275},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.4120883345603943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4024602174758911},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27053141593933105},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0781843364238739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022825","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":[],"awards":[{"id":"https://openalex.org/G4949534568","display_name":null,"funder_award_id":"MOST 111-2636-E-011-005","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320316499","display_name":"National Applied Research Laboratories","ror":"https://ror.org/05wcstg80"},{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2889048668","https://openalex.org/W2933138175","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2965373594","https://openalex.org/W2973049979","https://openalex.org/W2979826702","https://openalex.org/W3093452197","https://openalex.org/W3096297644","https://openalex.org/W3100308117","https://openalex.org/W3122931219","https://openalex.org/W3155427814","https://openalex.org/W3160622492","https://openalex.org/W3161048756","https://openalex.org/W3162249256","https://openalex.org/W3163388655","https://openalex.org/W3164692279","https://openalex.org/W3197140813","https://openalex.org/W3200601846","https://openalex.org/W3205920203","https://openalex.org/W3206573929","https://openalex.org/W3209059054","https://openalex.org/W4205442444","https://openalex.org/W4210758944","https://openalex.org/W4212774754","https://openalex.org/W4221151577","https://openalex.org/W4224916448","https://openalex.org/W4225299129","https://openalex.org/W4226521565","https://openalex.org/W4288086191","https://openalex.org/W4385245566","https://openalex.org/W6754473786","https://openalex.org/W6763701032","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6784698631"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W3096664139","https://openalex.org/W4385890381"],"abstract_inverted_index":{"Non-autoregressive":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"modeling":[5],"has":[6],"received":[7],"increasing":[8],"attention":[9],"recently":[10],"because":[11],"of":[12,42,53,67,127,138],"its":[13],"fast":[14],"decoding":[15],"speed":[16],"and":[17,72,93,132],"superior":[18],"performance.":[19],"Among":[20],"representatives,":[21],"methods":[22],"based":[23],"on":[24,129],"the":[25,36,40,51,57,94,100,104,118,130,136,139],"connectionist":[26],"temporal":[27],"classification":[28],"(CTC)":[29],"are":[30],"still":[31],"a":[32,47,61,68,73,89,109,111],"dominating":[33],"stream.":[34],"However,":[35],"theoretically":[37],"inherent":[38],"flaw,":[39],"assumption":[41],"independence":[43,106],"between":[44],"tokens,":[45],"creates":[46],"performance":[48],"barrier":[49],"for":[50,77],"school":[52],"works.":[54],"To":[55],"mitigate":[56],"challenge,":[58],"we":[59],"propose":[60],"context-aware":[62,74,113],"knowledge":[63,69],"transferring":[64,70],"strategy,":[65,76],"consisting":[66],"module":[71],"training":[75],"CTC-based":[78,114],"ASR.":[79],"The":[80],"former":[81],"is":[82,96,120],"designed":[83],"to":[84,98],"distill":[85],"linguistic":[86],"information":[87],"from":[88],"pre-trained":[90],"language":[91],"model,":[92],"latter":[95],"framed":[97],"modulate":[99],"limitations":[101],"caused":[102],"by":[103],"conditional":[105],"assumption.":[107],"As":[108],"result,":[110],"knowledge-injected":[112],"ASR":[115],"built":[116],"upon":[117],"wav2vec2.0":[119],"presented":[121],"in":[122],"this":[123],"paper.":[124],"A":[125],"series":[126],"experiments":[128],"AISHELL-1":[131],"AISHELL-2":[133],"datasets":[134],"demonstrate":[135],"effectiveness":[137],"proposed":[140],"method.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}