{"id":"https://openalex.org/W4387987051","doi":"https://doi.org/10.1109/lsp.2023.3328238","title":"A Transformer-Based End-to-End Automatic Speech Recognition Algorithm","display_name":"A Transformer-Based End-to-End Automatic Speech Recognition Algorithm","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4387987051","doi":"https://doi.org/10.1109/lsp.2023.3328238"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3328238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3328238","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5101497174","display_name":"Fang Dong","orcid":"https://orcid.org/0000-0003-3205-9931"},"institutions":[{"id":"https://openalex.org/I4400573310","display_name":"Hangzhou City University","ror":"https://ror.org/01wck0s05","country_code":null,"type":"education","lineage":["https://openalex.org/I4400573310"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Dong","raw_affiliation_strings":["School of Information and Electrical Engineering, Hangzhou City University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3205-9931","affiliations":[{"raw_affiliation_string":"School of Information and Electrical Engineering, Hangzhou City University, Hangzhou, China","institution_ids":["https://openalex.org/I4400573310"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032435542","display_name":"Yiyang Qian","orcid":"https://orcid.org/0009-0009-7310-5608"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiyang Qian","raw_affiliation_strings":["Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0009-7310-5608","affiliations":[{"raw_affiliation_string":"Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075474564","display_name":"Tianlei Wang","orcid":"https://orcid.org/0000-0002-4498-4326"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlei Wang","raw_affiliation_strings":["Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-4498-4326","affiliations":[{"raw_affiliation_string":"Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346924","display_name":"Peng Liu","orcid":"https://orcid.org/0009-0008-7485-5745"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["Zhejiang Baiying Technology Ltd. Company, Zhejiang, China"],"raw_orcid":"https://orcid.org/0009-0008-7485-5745","affiliations":[{"raw_affiliation_string":"Zhejiang Baiying Technology Ltd. Company, Zhejiang, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074063024","display_name":"Jiuwen Cao","orcid":"https://orcid.org/0000-0002-6480-5794"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiuwen Cao","raw_affiliation_strings":["Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6480-5794","affiliations":[{"raw_affiliation_string":"Machine Learning and I-health International Cooperation Base of Zhejiang Province, Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6345,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73872294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"1592","last_page":"1596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9959999918937683,"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":0.9909999966621399,"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":0.7657078504562378},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6510015726089478},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6492618322372437},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.6443665027618408},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5753503441810608},{"id":"https://openalex.org/keywords/prefix","display_name":"Prefix","score":0.544270396232605},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.5427018404006958},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.5292567610740662},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5036513209342957},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37508395314216614},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3130408525466919},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.25455114245414734},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.103543221950531}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657078504562378},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6510015726089478},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6492618322372437},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.6443665027618408},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5753503441810608},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.544270396232605},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.5427018404006958},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.5292567610740662},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5036513209342957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37508395314216614},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3130408525466919},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.25455114245414734},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.103543221950531},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/lsp.2023.3328238","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3328238","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7151297541","display_name":null,"funder_award_id":"U1909209","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1710082047","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2158903965","https://openalex.org/W2160815625","https://openalex.org/W2183341477","https://openalex.org/W2514741789","https://openalex.org/W2525778437","https://openalex.org/W2743392628","https://openalex.org/W2886319145","https://openalex.org/W2889048668","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2963211739","https://openalex.org/W2963242190","https://openalex.org/W2963414781","https://openalex.org/W2963590452","https://openalex.org/W2964089206","https://openalex.org/W2972389417","https://openalex.org/W2972625221","https://openalex.org/W2981413347","https://openalex.org/W3015995734","https://openalex.org/W3016256870","https://openalex.org/W3022882149","https://openalex.org/W3097794466","https://openalex.org/W3160413945","https://openalex.org/W3197478142","https://openalex.org/W3203701724","https://openalex.org/W4213423981","https://openalex.org/W4225289150","https://openalex.org/W4385245566","https://openalex.org/W6621543089","https://openalex.org/W6631190155","https://openalex.org/W6687566353","https://openalex.org/W6727690538","https://openalex.org/W6754473786","https://openalex.org/W6777472801"],"related_works":["https://openalex.org/W2350593162","https://openalex.org/W2390350206","https://openalex.org/W1969477129","https://openalex.org/W2921208823","https://openalex.org/W2353483812","https://openalex.org/W2131808775","https://openalex.org/W2130038259","https://openalex.org/W4307932641","https://openalex.org/W2903036216","https://openalex.org/W2088056149"],"abstract_inverted_index":{"End-to-End":[0],"(E2E)":[1],"automatic":[2],"speech":[3],"recognition":[4,101],"(ASR)":[5],"becomes":[6],"popular":[7],"recent":[8],"years":[9],"and":[10,36,82,93,133],"has":[11],"been":[12],"widely":[13],"used":[14],"in":[15,28,87],"many":[16],"applications.":[17],"However,":[18],"current":[19],"ASR":[20,49,97,126],"algorithms":[21],"are":[22,111],"usually":[23],"less":[24],"effective":[25],"when":[26],"applied":[27],"specific":[29],"applications":[30],"with":[31,117],"terminologies":[32],"such":[33],"as":[34],"medical":[35,118],"economic":[37],"fields.":[38],"To":[39,106],"address":[40],"this":[41],"issue,":[42],"we":[43],"propose":[44],"a":[45,71],"powerful":[46],"Transformer":[47],"based":[48],"decoding":[50],"method":[51],"for":[52],"beam":[53,57,68,89],"searching,":[54],"called":[55],"soft":[56],"pruning":[58],"algorithm":[59],"(SBPA).":[60],"SBPA":[61,92],"can":[62,98],"dynamically":[63],"adjust":[64],"the":[65,79,88,95,108,124],"width":[66],"of":[67],"search.":[69,90],"Meanwhile,":[70],"prefix":[72],"module":[73],"(PM)":[74],"is":[75,121],"added":[76],"to":[77],"access":[78],"contextual":[80],"information":[81],"avoid":[83],"removing":[84],"professional":[85,104,132],"words":[86],"Combining":[91],"PM,":[94],"proposed":[96,125],"achieve":[99],"promising":[100],"performance":[102,129],"on":[103,113,130],"terminologies.":[105],"verify":[107],"effectiveness,":[109],"experiments":[110],"conducted":[112],"real-world":[114],"conversation":[115],"data":[116],"terminology.":[119],"It":[120],"shown":[122],"that":[123],"achieved":[127],"significant":[128],"both":[131],"regular":[134],"words.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}