{"id":"https://openalex.org/W4319586262","doi":"https://doi.org/10.1109/iscslp57327.2022.10037993","title":"Efficient Conformer-Based CTC Model for Intelligent Cockpit Speech Recognition","display_name":"Efficient Conformer-Based CTC Model for Intelligent Cockpit Speech Recognition","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586262","doi":"https://doi.org/10.1109/iscslp57327.2022.10037993"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037993","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5051734568","display_name":"Hanzhi Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hanzhi Guo","raw_affiliation_strings":["The University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090679057","display_name":"Yunshu Chen","orcid":"https://orcid.org/0000-0002-2728-0933"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yunshu Chen","raw_affiliation_strings":["The University of Sydney"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020275154","display_name":"Xukang Xie","orcid":"https://orcid.org/0000-0003-1378-0117"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xukang Xie","raw_affiliation_strings":["NIO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NIO","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109577487","display_name":"Gaopeng Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaopeng Xu","raw_affiliation_strings":["NIO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NIO","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047578156","display_name":"Wei Guo","orcid":"https://orcid.org/0000-0002-3017-5464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Guo","raw_affiliation_strings":["NIO"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NIO","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"522","last_page":"526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9993000030517578,"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":0.9968000054359436,"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":0.7333500385284424},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6651350855827332},{"id":"https://openalex.org/keywords/track","display_name":"Track (disk drive)","score":0.6463810801506042},{"id":"https://openalex.org/keywords/cockpit","display_name":"Cockpit","score":0.6060895919799805},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.46663862466812134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45100605487823486},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.44406747817993164},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4358021020889282},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15175014734268188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7333500385284424},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6651350855827332},{"id":"https://openalex.org/C89992363","wikidata":"https://www.wikidata.org/wiki/Q5961558","display_name":"Track (disk drive)","level":2,"score":0.6463810801506042},{"id":"https://openalex.org/C30322324","wikidata":"https://www.wikidata.org/wiki/Q194156","display_name":"Cockpit","level":2,"score":0.6060895919799805},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.46663862466812134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45100605487823486},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.44406747817993164},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4358021020889282},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15175014734268188},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037993","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W187434241","https://openalex.org/W2113932204","https://openalex.org/W2119445797","https://openalex.org/W2135823751","https://openalex.org/W2403555780","https://openalex.org/W2407080277","https://openalex.org/W2746475861","https://openalex.org/W2766219058","https://openalex.org/W2769205094","https://openalex.org/W2936774411","https://openalex.org/W3015735225","https://openalex.org/W3034175346","https://openalex.org/W3045672834","https://openalex.org/W3084110843","https://openalex.org/W3090831112","https://openalex.org/W3097777922","https://openalex.org/W3109689953","https://openalex.org/W3162249256","https://openalex.org/W4221167707","https://openalex.org/W4225302952","https://openalex.org/W4226266037","https://openalex.org/W4281722345","https://openalex.org/W4319586912","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W289003589","https://openalex.org/W2350798740","https://openalex.org/W4285264191","https://openalex.org/W2998452958","https://openalex.org/W2006341478","https://openalex.org/W2548061885","https://openalex.org/W333251188","https://openalex.org/W3180504149","https://openalex.org/W2036761630","https://openalex.org/W2216022431"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,106],"discuss":[4],"the":[5,16,70,84,91,112,116,131,139,146],"rationale":[6],"of":[7,33,69,97,130,152],"our":[8],"work":[9],"for":[10,54],"automatic":[11],"speech":[12],"recognition":[13],"(ASR)":[14],"in":[15,72,90,145],"ISCSLP":[17],"2022":[18],"Intelligent":[19,55],"Cockpit":[20,56],"Speech":[21,57],"Recognition":[22],"Challenge":[23],"and":[24,124],"provide":[25],"a":[26,31,95,120,150],"detailed":[27],"description.":[28],"We":[29],"proposed":[30],"combination":[32,50],"intermediate":[34],"CTC-based":[35],"loss":[36],"regularization(Inter-CTC)":[37],"with":[38,44,94,119,149],"self-conditioned":[39],"folded":[40],"encoders,":[41],"also":[42],"deployed":[43],"TLG":[45],"attention-rescore-based":[46],"acoustic":[47],"model.":[48],"This":[49],"finds":[51],"good":[52],"solutions":[53],"recognition,":[58],"as":[59],"it":[60],"makes":[61],"accuracy":[62],"improvements.":[63],"The":[64,128],"Character":[65],"Error":[66],"Rate":[67],"(CER)":[68],"model":[71,76,103,114,134],"Track":[73,100,122,125,132],"II":[74,126,133],"(Unlimited":[75],"size":[77,104],"track)":[78],"decreased":[79],"by":[80,136],"38.12%":[81],"compared":[82],"to":[83,110],"baseline":[85,140],"model,":[86,141],"achieving":[87,142],"second":[88],"place":[89,144],"ranking":[92,147],"period":[93,148],"CER":[96,129,151],"9.86%.":[98],"For":[99],"I":[101,123],"(Limited":[102],"track),":[105],"apply":[107],"knowledge":[108],"distillation":[109],"train":[111],"Teacher-Student":[113],"from":[115,138],"unlimited":[117],"track,":[118],"combining":[121],"Kloss.":[127],"drops":[135],"40.18%":[137],"third":[143],"13.39%.":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}