{"id":"https://openalex.org/W4402979839","doi":"https://doi.org/10.1109/icme57554.2024.10687992","title":"SPformer: Hybrid Sequential-Parallel Architectures for Automatic Speech Recognition","display_name":"SPformer: Hybrid Sequential-Parallel Architectures for Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402979839","doi":"https://doi.org/10.1109/icme57554.2024.10687992"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687992","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5111346917","display_name":"Mingdong Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingdong Yu","raw_affiliation_strings":["Yanbian University,Yanji,China"],"affiliations":[{"raw_affiliation_string":"Yanbian University,Yanji,China","institution_ids":["https://openalex.org/I1793135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089390321","display_name":"Xiaofeng Jin","orcid":"https://orcid.org/0000-0003-1892-3439"},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Jin","raw_affiliation_strings":["Yanbian University,Yanji,China"],"affiliations":[{"raw_affiliation_string":"Yanbian University,Yanji,China","institution_ids":["https://openalex.org/I1793135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100783080","display_name":"Guirong Wang","orcid":"https://orcid.org/0000-0002-3288-8572"},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guirong Wang","raw_affiliation_strings":["Yanbian University,Yanji,China"],"affiliations":[{"raw_affiliation_string":"Yanbian University,Yanji,China","institution_ids":["https://openalex.org/I1793135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100408160","display_name":"Bo Wang","orcid":"https://orcid.org/0000-0002-9620-3413"},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Wang","raw_affiliation_strings":["Yanbian University,Yanji,China"],"affiliations":[{"raw_affiliation_string":"Yanbian University,Yanji,China","institution_ids":["https://openalex.org/I1793135"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100434198","display_name":"Jiaqi Chen","orcid":"https://orcid.org/0000-0002-6368-6164"},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Chen","raw_affiliation_strings":["Yanbian University,Yanji,China"],"affiliations":[{"raw_affiliation_string":"Yanbian University,Yanji,China","institution_ids":["https://openalex.org/I1793135"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5111346917"],"corresponding_institution_ids":["https://openalex.org/I1793135"],"apc_list":null,"apc_paid":null,"fwci":0.3641,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67596063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9843000173568726,"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":0.9843000173568726,"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":0.9671000242233276,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9483000040054321,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8250129222869873},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.646247386932373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35467642545700073},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34142252802848816}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8250129222869873},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.646247386932373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35467642545700073},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34142252802848816}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687992","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687992","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320330447","display_name":"Yanbian University","ror":"https://ror.org/039xnh269"}],"has_content":{"pdf":false,"grobid_xml":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/W4395014643"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"the":[3,18,36,53,77],"capability":[4],"to":[5],"interact":[6],"with":[7,50],"multi-scale":[8],"information":[9],"has":[10],"been":[11],"regarded":[12],"as":[13,112],"a":[14],"crucial":[15],"aspect":[16],"of":[17,108],"Automatic":[19],"Speech":[20],"Recognition":[21],"(ASR)":[22],"encoder\u2019s":[23],"abilities.":[24],"Conformer":[25,109],"and":[26,30,40,56,68,83,93,104,110],"Branchformer,":[27],"representing":[28],"sequential":[29,47,81],"parallel":[31,61,84],"architectural":[32],"designs,":[33],"respectively,":[34],"facilitate":[35],"interaction":[37,54,90],"between":[38,91],"global":[39],"local":[41],"information,":[42],"achieving":[43],"state-of-the-art":[44],"performance.":[45],"However,":[46],"architectures":[48,62],"struggle":[49],"explicability":[51],"in":[52,65],"process":[55],"rigid":[57],"model":[58],"design,":[59],"while":[60,95],"face":[63],"challenges":[64],"integration":[66],"difficulties":[67],"limited":[69],"interaction.":[70],"To":[71],"address":[72],"these":[73],"issues,":[74],"we":[75],"propose":[76],"SPformer,":[78],"effectively":[79],"combining":[80],"connection":[82],"branch":[85,97],"architectures.":[86],"It":[87],"allows":[88],"dynamic":[89],"convolution":[92],"self-attention":[94],"utilizing":[96],"structures.":[98],"The":[99],"SPformer\u2019s":[100],"performance,":[101],"both":[102],"in-domain":[103],"out-of-domain,":[105],"surpasses":[106],"that":[107],"E-Branchformer,":[111],"demonstrated":[113],"by":[114],"our":[115],"experiments":[116],"on":[117],"public":[118],"ASR":[119],"datasets.":[120]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}