{"id":"https://openalex.org/W4280606616","doi":"https://doi.org/10.3390/info13050250","title":"LAS-Transformer: An Enhanced Transformer Based on the Local Attention Mechanism for Speech Recognition","display_name":"LAS-Transformer: An Enhanced Transformer Based on the Local Attention Mechanism for Speech Recognition","publication_year":2022,"publication_date":"2022-05-13","ids":{"openalex":"https://openalex.org/W4280606616","doi":"https://doi.org/10.3390/info13050250"},"language":"en","primary_location":{"id":"doi:10.3390/info13050250","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info13050250","pdf_url":"https://www.mdpi.com/2078-2489/13/5/250/pdf?version=1652424997","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/13/5/250/pdf?version=1652424997","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023876632","display_name":"Pengbin Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengbin Fu","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053095755","display_name":"Daxing Liu","orcid":"https://orcid.org/0000-0001-6559-571X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daxing Liu","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"],"raw_orcid":"https://orcid.org/0000-0001-6559-571X","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037565330","display_name":"Huirong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huirong Yang","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023876632"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.2485,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82694757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"13","issue":"5","first_page":"250","last_page":"250"},"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":0.9987000226974487,"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":0.9977999925613403,"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":0.7442909479141235},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7391623258590698},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.625203013420105},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5583006739616394},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5515807867050171},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5352514386177063},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5237933397293091},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.4998466968536377},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.48667556047439575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46253326535224915},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4280718266963959},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.414937287569046},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3962112069129944},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35388797521591187},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10956454277038574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7442909479141235},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7391623258590698},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.625203013420105},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5583006739616394},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5515807867050171},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5352514386177063},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5237933397293091},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.4998466968536377},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.48667556047439575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46253326535224915},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4280718266963959},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.414937287569046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3962112069129944},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35388797521591187},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10956454277038574},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info13050250","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info13050250","pdf_url":"https://www.mdpi.com/2078-2489/13/5/250/pdf?version=1652424997","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:467ea8b0c00242c28b20da12806c6331","is_oa":true,"landing_page_url":"https://doaj.org/article/467ea8b0c00242c28b20da12806c6331","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 13, Iss 5, p 250 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2078-2489/13/5/250/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/info13050250","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information; Volume 13; Issue 5; Pages: 250","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/info13050250","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info13050250","pdf_url":"https://www.mdpi.com/2078-2489/13/5/250/pdf?version=1652424997","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4746619204","display_name":null,"funder_award_id":"61772048","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4280606616.pdf","grobid_xml":"https://content.openalex.org/works/W4280606616.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2966661","https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2144499799","https://openalex.org/W2158373110","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2531409750","https://openalex.org/W2889163603","https://openalex.org/W2892009249","https://openalex.org/W2915716523","https://openalex.org/W2936774411","https://openalex.org/W2962826786","https://openalex.org/W2963414781","https://openalex.org/W2964110616","https://openalex.org/W2972389417","https://openalex.org/W2972818416","https://openalex.org/W2981857663","https://openalex.org/W3007328579","https://openalex.org/W3015537910","https://openalex.org/W3097777922","https://openalex.org/W3197507772","https://openalex.org/W6623517193","https://openalex.org/W6739901393","https://openalex.org/W6772381481"],"related_works":["https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048"],"abstract_inverted_index":{"Recently,":[0],"Transformer-based":[1],"models":[2,13],"have":[3],"shown":[4],"promising":[5],"results":[6,171],"in":[7,47],"automatic":[8],"speech":[9,40,62,70,91],"recognition":[10,63],"(ASR),":[11],"outperforming":[12],"based":[14,101],"on":[15,102,134],"recurrent":[16],"neural":[17,22],"networks":[18,23],"(RNNs)":[19],"and":[20,110,158],"convolutional":[21],"(CNNs).":[24],"However,":[25],"directly":[26],"applying":[27],"a":[28,48,56,144],"Transformer":[29,59,89],"to":[30,83,106,119,125,167],"the":[31,37,44,66,85,88,107,116,121,129,135,160,168],"ASR":[32],"task":[33],"does":[34],"not":[35],"exploit":[36],"correlation":[38,68],"among":[39,69],"frames":[41],"effectively,":[42],"leaving":[43],"model":[45,60,152],"trapped":[46],"sub-optimal":[49],"solution.":[50],"To":[51],"this":[52],"end,":[53],"we":[54,73,97],"propose":[55],"local":[57,99],"attention":[58,100],"for":[61,90],"that":[64,139],"combines":[65],"high":[67],"frames.":[71],"Specifically,":[72],"use":[74],"relative":[75],"positional":[76,81,104],"embedding,":[77,82],"rather":[78],"than":[79],"absolute":[80],"improve":[84],"generalization":[86],"of":[87,93,148],"sequences":[92],"different":[94],"lengths.":[95],"Secondly,":[96],"add":[98],"parametric":[103],"relations":[105],"self-attentive":[108,117],"module":[109,118],"explicitly":[111],"incorporate":[112],"prior":[113],"knowledge":[114],"into":[115],"make":[120],"training":[122],"process":[123],"insensitive":[124],"hyperparameters,":[126],"thus":[127],"improving":[128],"performance.":[130],"Experiments":[131],"carried":[132],"out":[133],"LibriSpeech":[136],"dataset":[137],"show":[138],"our":[140],"proposed":[141],"approach":[142],"achieves":[143],"word":[145,161],"error":[146,162],"rate":[147,163],"2.3/5.5%":[149],"by":[150,164],"language":[151],"fusion":[153],"without":[154],"any":[155],"external":[156],"data":[157],"reduces":[159],"17.8/9.8%":[165],"compared":[166],"baseline.":[169],"The":[170],"are":[172],"also":[173],"close":[174],"to,":[175],"or":[176],"better":[177],"than,":[178],"other":[179],"state-of-the-art":[180],"end-to-end":[181],"models.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}