{"id":"https://openalex.org/W4402978869","doi":"https://doi.org/10.1109/access.2024.3471183","title":"Ubranch Conformer: Integrating Up-Down Sampling and Branch Attention for Speech Recognition","display_name":"Ubranch Conformer: Integrating Up-Down Sampling and Branch Attention for Speech Recognition","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402978869","doi":"https://doi.org/10.1109/access.2024.3471183"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3471183","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3471183","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dx.doi.org/10.1109/access.2024.3471183","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yang Yang","orcid":"https://orcid.org/0009-0009-2008-9181"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China"],"raw_orcid":"https://orcid.org/0009-0009-2008-9181","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102813327","display_name":"Yao Feng","orcid":"https://orcid.org/0000-0002-9481-9783"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Yao","raw_affiliation_strings":["School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108993591","display_name":"Mingke Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingke Liao","raw_affiliation_strings":["School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China","institution_ids":["https://openalex.org/I91125648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084276385","display_name":"Yucheng Huang","orcid":"https://orcid.org/0009-0002-5662-7040"},"institutions":[{"id":"https://openalex.org/I91125648","display_name":"Wuhan Institute of Technology","ror":"https://ror.org/04jcykh16","country_code":"CN","type":"education","lineage":["https://openalex.org/I91125648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yucheng Huang","raw_affiliation_strings":["School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China","institution_ids":["https://openalex.org/I91125648"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91125648"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2778,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62652026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"144684","last_page":"144697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7468000054359436,"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":0.7468000054359436,"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":0.6844000220298767,"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":0.6993931531906128},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5475921034812927},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4420928359031677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3752896189689636},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35950225591659546},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12331435084342957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6993931531906128},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5475921034812927},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4420928359031677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3752896189689636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35950225591659546},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12331435084342957},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3471183","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3471183","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e877a9db23904a18bc3348ad11b84b8d","is_oa":true,"landing_page_url":"https://doaj.org/article/e877a9db23904a18bc3348ad11b84b8d","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":"IEEE Access, Vol 12, Pp 144684-144697 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3471183","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3471183","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Conformer":[0,30,164],"has":[1],"become":[2],"one":[3],"of":[4,12,107,170],"the":[5,10,39,82,105,113,145],"most":[6],"popular":[7],"models":[8,31],"in":[9,38,49,58,112,150],"field":[11],"automatic":[13],"speech":[14,18],"recognition,":[15],"achieving":[16],"superior":[17],"recognition":[19],"performance":[20,171,182],"by":[21],"integrating":[22],"a":[23,67,95,125,166,178],"convolutional":[24],"module":[25],"into":[26],"Transformer.":[27],"However,":[28],"existing":[29,174],"face":[32],"challenges":[33],"with":[34,98,141],"high":[35],"computational":[36,90],"complexity":[37,118],"attention":[40,79,134,142],"mechanism":[41],"when":[42],"capturing":[43,151],"global":[44,152],"dependencies,":[45,53],"and":[46,77,88,135,148,153,176,183],"lack":[47],"flexibility":[48,149],"dynamically":[50],"adjusting":[51],"local":[52,154],"which":[54,73],"limits":[55],"their":[56],"efficiency":[57],"processing":[59],"sequences.":[60],"To":[61],"address":[62],"these":[63],"challenges,":[64],"we":[65,93,123],"propose":[66],"new":[68,96],"model":[69],"called":[70],"Ubranch":[71,163],"Conformer,":[72],"combines":[74],"Up-Down":[75,100],"sampling":[76,101,106],"branch":[78,133],"to":[80,84,143,173],"enhance":[81],"ability":[83,147],"capture":[85],"input":[86],"information":[87],"reduce":[89],"complexity.":[91,184],"First,":[92],"designed":[94],"architecture":[97],"an":[99],"strategy":[102],"that":[103,130,161],"adjusts":[104],"embedded":[108],"sequences":[109],"between":[110,181],"blocks":[111],"model\u2019s":[114,146],"intermediate":[115],"layers,":[116],"reducing":[117],"without":[119],"compromising":[120],"efficiency.":[121],"Second,":[122],"introduce":[124],"more":[126,167],"efficient":[127],"block":[128],"structure":[129],"mainly":[131],"contains":[132],"convolution":[136,140],"gate":[137],"modules,":[138],"combining":[139],"improve":[144],"dependencies.":[155],"Experiments":[156],"on":[157],"multiple":[158],"datasets":[159],"show":[160],"our":[162],"achieves":[165,177],"advanced":[168],"level":[169],"compared":[172],"models,":[175],"good":[179],"balance":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2025-10-10T00:00:00"}