{"id":"https://openalex.org/W4407153583","doi":"https://doi.org/10.1186/s13636-025-00394-6","title":"A speech recognition method with enhanced transformer decoder","display_name":"A speech recognition method with enhanced transformer decoder","publication_year":2025,"publication_date":"2025-02-05","ids":{"openalex":"https://openalex.org/W4407153583","doi":"https://doi.org/10.1186/s13636-025-00394-6"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-025-00394-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00394-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-025-00394-6.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s13636-025-00394-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hengbo Hu","orcid":"https://orcid.org/0009-0007-1172-1152"},"institutions":[{"id":"https://openalex.org/I4210126172","display_name":"Henan Communication Science and Technology Research Institute (China)","ror":"https://ror.org/027s8b340","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126172"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hengbo Hu","raw_affiliation_strings":["Research and Development Department 1 - Intelligent Speech Technology Team, Zhengzhou Xinda Institute of Advanced Technology, Lianhua Street, Zhengzhou, 450000, Henan, China"],"raw_orcid":"https://orcid.org/0009-0007-1172-1152","affiliations":[{"raw_affiliation_string":"Research and Development Department 1 - Intelligent Speech Technology Team, Zhengzhou Xinda Institute of Advanced Technology, Lianhua Street, Zhengzhou, 450000, Henan, China","institution_ids":["https://openalex.org/I4210126172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101583904","display_name":"Tong Niu","orcid":"https://orcid.org/0000-0002-0128-9657"},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]},{"id":"https://openalex.org/I4210094772","display_name":"Henan University of Engineering","ror":"https://ror.org/007wym039","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210094772"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Niu","raw_affiliation_strings":["School of Information Systems Engineering, University of Information Engineering, Science Avenue, Zhengzhou, 450000, Henan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Systems Engineering, University of Information Engineering, Science Avenue, Zhengzhou, 450000, Henan, China","institution_ids":["https://openalex.org/I169689159","https://openalex.org/I4210094772"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090685598","display_name":"Zhenhua He","orcid":"https://orcid.org/0000-0003-1706-3561"},"institutions":[{"id":"https://openalex.org/I4210126172","display_name":"Henan Communication Science and Technology Research Institute (China)","ror":"https://ror.org/027s8b340","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126172"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua He","raw_affiliation_strings":["Research and Development Department 1 - Intelligent Speech Technology Team, Zhengzhou Xinda Institute of Advanced Technology, Lianhua Street, Zhengzhou, 450000, Henan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Department 1 - Intelligent Speech Technology Team, Zhengzhou Xinda Institute of Advanced Technology, Lianhua Street, Zhengzhou, 450000, Henan, China","institution_ids":["https://openalex.org/I4210126172"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210126172"],"apc_list":{"value":1635,"currency":"USD","value_usd":1635},"apc_paid":{"value":1635,"currency":"USD","value_usd":1635},"fwci":1.2644,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8248878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"2025","issue":"1","first_page":null,"last_page":null},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9923999905586243,"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":0.9317072629928589},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7314796447753906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6686463952064514},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3218645453453064},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.17088139057159424},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12426528334617615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9317072629928589},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7314796447753906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6686463952064514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3218645453453064},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.17088139057159424},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12426528334617615},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-025-00394-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00394-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-025-00394-6.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5b6fd2d632584e43854bd517d0fc49eb","is_oa":false,"landing_page_url":"https://doaj.org/article/5b6fd2d632584e43854bd517d0fc49eb","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2025, Iss 1, Pp 1-12 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-025-00394-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-025-00394-6","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13636-025-00394-6.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2727895085","display_name":null,"funder_award_id":"232300421240","funder_id":"https://openalex.org/F4320323845","funder_display_name":"Natural Science Foundation of Henan Province"},{"id":"https://openalex.org/G6545306923","display_name":null,"funder_award_id":"232300421240","funder_id":"https://openalex.org/F4320310121","funder_display_name":"Natural Science Foundation of Jilin Province"},{"id":"https://openalex.org/G7804056170","display_name":null,"funder_award_id":"62171470","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8938656053","display_name":null,"funder_award_id":"234200510019","funder_id":"https://openalex.org/F4320335446","funder_display_name":"Chongqing Youth Science and Technology Talent Training Project"}],"funders":[{"id":"https://openalex.org/F4320310121","display_name":"Natural Science Foundation of Jilin Province","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323845","display_name":"Natural Science Foundation of Henan Province","ror":null},{"id":"https://openalex.org/F4320335446","display_name":"Chongqing Youth Science and Technology Talent Training Project","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407153583.pdf","grobid_xml":"https://content.openalex.org/works/W4407153583.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2117862860","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2144499799","https://openalex.org/W2160815625","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2739883972","https://openalex.org/W2888779557","https://openalex.org/W2892009249","https://openalex.org/W2938286689","https://openalex.org/W2962826786","https://openalex.org/W2963240019","https://openalex.org/W2963242190","https://openalex.org/W2963362078","https://openalex.org/W2963925437","https://openalex.org/W3015995734","https://openalex.org/W3096552437","https://openalex.org/W3097777922","https://openalex.org/W3151130473","https://openalex.org/W4322732039","https://openalex.org/W6600459515","https://openalex.org/W6600575766","https://openalex.org/W6605299328","https://openalex.org/W6609966703","https://openalex.org/W6702248584","https://openalex.org/W6713762819"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Addressing":[0],"the":[1,4,27,43,48,72,76,97,104,109,122,127,136,139],"issue":[2],"that":[3,102],"Transformer":[5,49,123],"decoder":[6,39,50,111],"struggles":[7],"to":[8,65,83,121],"capture":[9,66],"local":[10,67],"features":[11,68],"for":[12],"monotonic":[13],"alignment":[14],"in":[15,47,116],"speech":[16,32],"recognition,":[17],"and":[18,41,54,75],"simultaneously":[19],"incorporating":[20],"language":[21,57,78,128],"model":[22,34,58,79,129,142],"cold":[23,91,140],"fusion":[24,92],"training":[25],"into":[26,51],"decoder,":[28],"an":[29],"enhanced":[30,38,110],"decoder-based":[31],"recognition":[33],"is":[35,81,106,130,143],"investigated.":[36],"The":[37,60],"separates":[40],"combines":[42],"two":[44],"attention":[45],"mechanisms":[46],"cross-attention":[52,61],"layers":[53,62],"a":[55,107,113],"self-attention":[56,77],"module.":[59],"are":[63],"utilized":[64],"more":[69],"efficiently":[70],"from":[71],"encoder":[73,105],"output,":[74],"module":[80],"used":[82],"pre-train":[84],"with":[85,132],"additional":[86],"domain-related":[87],"text,":[88],"followed":[89],"by":[90],"training.":[93],"Experimental":[94],"results":[95],"on":[96],"Mandarin":[98],"Aishell-1":[99],"dataset":[100],"demonstrate":[101],"when":[103,126],"Conformer,":[108],"achieves":[112],"16.1%":[114],"reduction":[115],"character":[117],"error":[118],"rate":[119],"compared":[120],"decoder.":[124],"Furthermore,":[125],"pre-trained":[131],"suitable":[133],"text":[134],"data,":[135],"performance":[137],"of":[138],"fusion-trained":[141],"further":[144],"enhanced.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}