{"id":"https://openalex.org/W4200200210","doi":"https://doi.org/10.1109/iccais52680.2021.9624549","title":"An Improved Speech Recognition System Based on Transformer Language Model","display_name":"An Improved Speech Recognition System Based on Transformer Language Model","publication_year":2021,"publication_date":"2021-10-14","ids":{"openalex":"https://openalex.org/W4200200210","doi":"https://doi.org/10.1109/iccais52680.2021.9624549"},"language":"en","primary_location":{"id":"doi:10.1109/iccais52680.2021.9624549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais52680.2021.9624549","pdf_url":null,"source":{"id":"https://openalex.org/S4363608071","display_name":"2021 International Conference on Control, Automation and Information Sciences (ICCAIS)","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":"2021 International Conference on Control, Automation and Information Sciences (ICCAIS)","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/A5000331794","display_name":"Yue Qi","orcid":"https://orcid.org/0000-0002-7546-0613"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Yue","raw_affiliation_strings":["Xi'an University of Posts & Telecommunications, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an University of Posts & Telecommunications, Xi'an, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011930080","display_name":"Weiliang Shi","orcid":"https://orcid.org/0000-0002-5659-1204"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiliang Shi","raw_affiliation_strings":["Xi'an University of Posts & Telecommunications, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an University of Posts & Telecommunications, Xi'an, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069832491","display_name":"Yi He","orcid":"https://orcid.org/0000-0002-6925-7299"},"institutions":[{"id":"https://openalex.org/I4210148225","display_name":"China State Construction Engineering (China)","ror":"https://ror.org/03kgcsq08","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210148225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi He","raw_affiliation_strings":["China Construction Second Bureau Third Construction Engineering Company Limited, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"China Construction Second Bureau Third Construction Engineering Company Limited, Shenzhen, China","institution_ids":["https://openalex.org/I4210148225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867736","display_name":"Jing Chu","orcid":"https://orcid.org/0000-0002-9325-4004"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Chu","raw_affiliation_strings":["Xi'an University of Posts & Telecommunications, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an University of Posts & Telecommunications, Xi'an, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100956303","display_name":"Han Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Han","raw_affiliation_strings":["Xi'an University of Posts & Telecommunications, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an University of Posts & Telecommunications, Xi'an, China","institution_ids":["https://openalex.org/I4210136859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072145686","display_name":"Xiaokai Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaokai Han","raw_affiliation_strings":["Xi'an University of Posts & Telecommunications, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an University of Posts & Telecommunications, Xi'an, China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5000331794"],"corresponding_institution_ids":["https://openalex.org/I4210136859"],"apc_list":null,"apc_paid":null,"fwci":0.2513,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50822584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"920","last_page":"925"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9961000084877014,"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":0.9860000014305115,"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":0.8334908485412598},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7477614879608154},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7048827409744263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6005510091781616},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.598783552646637},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5684001445770264},{"id":"https://openalex.org/keywords/cache-language-model","display_name":"Cache language model","score":0.567995548248291},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5357000231742859},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5328474640846252},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4666196405887604},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4156843423843384},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.37119850516319275},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3706817924976349},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.28053784370422363},{"id":"https://openalex.org/keywords/universal-networking-language","display_name":"Universal Networking Language","score":0.1569330096244812},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10575783252716064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8334908485412598},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7477614879608154},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7048827409744263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6005510091781616},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.598783552646637},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5684001445770264},{"id":"https://openalex.org/C39608478","wikidata":"https://www.wikidata.org/wiki/Q5015979","display_name":"Cache language model","level":5,"score":0.567995548248291},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5357000231742859},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5328474640846252},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4666196405887604},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4156843423843384},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.37119850516319275},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3706817924976349},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28053784370422363},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.1569330096244812},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10575783252716064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C129353971","wikidata":"https://www.wikidata.org/wiki/Q5156949","display_name":"Comprehension approach","level":3,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccais52680.2021.9624549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccais52680.2021.9624549","pdf_url":null,"source":{"id":"https://openalex.org/S4363608071","display_name":"2021 International Conference on Control, Automation and Information Sciences (ICCAIS)","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":"2021 International Conference on Control, Automation and Information Sciences (ICCAIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1977808218","https://openalex.org/W2005687631","https://openalex.org/W2127141656","https://openalex.org/W2253429366","https://openalex.org/W2604158577","https://openalex.org/W2766219058","https://openalex.org/W2963414781","https://openalex.org/W2963946371","https://openalex.org/W2980722219","https://openalex.org/W3154932257"],"related_works":["https://openalex.org/W4255155614","https://openalex.org/W2394860946","https://openalex.org/W761725120","https://openalex.org/W2897427480","https://openalex.org/W2140351598","https://openalex.org/W3021690593","https://openalex.org/W2888189389","https://openalex.org/W2161188302","https://openalex.org/W2402899696","https://openalex.org/W2141404479"],"abstract_inverted_index":{"With":[0],"the":[1,80,99,103],"application":[2],"of":[3,25,102],"deep":[4,63],"learning":[5],"in":[6,17],"speech":[7,18,107],"recognition":[8,100,108],"technology,":[9],"many":[10],"neural":[11,64],"network-based":[12,65],"model":[13,84,106],"structures":[14],"have":[15,32],"emerged":[16],"recognition,":[19],"while":[20],"as":[21,41,95],"another":[22],"important":[23],"part":[24],"language":[26,30,83,88,105],"models,":[27],"traditional":[28,81],"statistical":[29,47,82],"models":[31],"not":[33],"been":[34],"further":[35],"developed":[36],"due":[37],"to":[38,78],"drawbacks":[39],"such":[40,94],"oversized":[42],"parameters,":[43],"purely":[44],"based":[45],"on":[46,91],"frequencies,":[48],"and":[49],"poor":[50],"generalization":[51],"ability.":[52],"To":[53],"address":[54],"those":[55],"drawbacks,":[56],"this":[57],"paper":[58],"uses":[59],"a":[60,73,86],"fully":[61],"convolutional":[62],"acoustic":[66],"model,":[67],"which":[68],"is":[69,110],"then":[70],"combined":[71],"with":[72,85],"connected":[74],"temporal":[75],"classification":[76],"method":[77],"replace":[79],"Transformer-based":[87,104],"model.":[89],"Experiments":[90],"several":[92],"datasets":[93],"THCHS30":[96],"show":[97],"that":[98],"effectiveness":[101],"system":[109],"effectively":[111],"improved.":[112]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
