{"id":"https://openalex.org/W4390691989","doi":"https://doi.org/10.1109/lsp.2024.3352489","title":"SSCFormer: Push the Limit of Chunk-Wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution","display_name":"SSCFormer: Push the Limit of Chunk-Wise Conformer for Streaming ASR Using Sequentially Sampled Chunks and Chunked Causal Convolution","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390691989","doi":"https://doi.org/10.1109/lsp.2024.3352489"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3352489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3352489","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/A5101840024","display_name":"Fangyuan Wang","orcid":"https://orcid.org/0000-0002-6482-4522"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyuan Wang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6482-4522","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652392","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-8884-0447"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8884-0447","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1111-1529","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6109,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70452434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"31","issue":null,"first_page":"421","last_page":"425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9997000098228455,"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":0.9997000098228455,"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":0.8280184864997864},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7087640762329102},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.5886476039886475},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5780502557754517},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5391891598701477},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.535065233707428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36878347396850586},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3377067446708679},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3368144631385803},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15918445587158203}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8280184864997864},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7087640762329102},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5886476039886475},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5780502557754517},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5391891598701477},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.535065233707428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36878347396850586},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3377067446708679},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3368144631385803},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15918445587158203},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3352489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3352489","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":[{"id":"https://metadata.un.org/sdg/4","score":0.4399999976158142,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2936774411","https://openalex.org/W2963242190","https://openalex.org/W2963827914","https://openalex.org/W2963970535","https://openalex.org/W3015671919","https://openalex.org/W3015974384","https://openalex.org/W3095311338","https://openalex.org/W3096123040","https://openalex.org/W3096702180","https://openalex.org/W3096888553","https://openalex.org/W3097125541","https://openalex.org/W3097777922","https://openalex.org/W3111562797","https://openalex.org/W3148986242","https://openalex.org/W3161873870","https://openalex.org/W3162016613","https://openalex.org/W3162665866","https://openalex.org/W3163793923","https://openalex.org/W3170405627","https://openalex.org/W3197654132","https://openalex.org/W4221167707","https://openalex.org/W4296068782","https://openalex.org/W4296070361","https://openalex.org/W4365794755","https://openalex.org/W6739901393","https://openalex.org/W6784800133","https://openalex.org/W6787040858","https://openalex.org/W6793772276","https://openalex.org/W6797037654","https://openalex.org/W6838276489"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W4231775656","https://openalex.org/W2046435967","https://openalex.org/W2383646825","https://openalex.org/W2371018915","https://openalex.org/W2354191502","https://openalex.org/W1972225038","https://openalex.org/W2351938575","https://openalex.org/W2388359778","https://openalex.org/W2477549100"],"abstract_inverted_index":{"Currently,":[0],"the":[1,25,38,45,48,57,74,83,126,154],"chunk-wise":[2,77,130,155],"schemes":[3],"are":[4,21],"often":[5],"used":[6],"to":[7,14,23,72,100,107,123,163],"make":[8],"Automatic":[9],"Speech":[10],"Recognition":[11],"(ASR)":[12],"models":[13],"support":[15,29],"streaming":[16,64,80],"deployment.":[17],"However,":[18],"existing":[19],"approaches":[20],"unable":[22],"capture":[24,125],"global":[26],"context,":[27],"lack":[28],"for":[30,37,79],"parallel":[31],"training,":[32],"or":[33],"exhibit":[34],"quadratic":[35],"complexity":[36],"computation":[39,157],"of":[40,76],"multi-head":[41],"self-attention":[42],"(MHSA).":[43],"On":[44],"other":[46],"side,":[47],"causal":[49],"convolution,":[50],"no":[51],"future":[52,131],"context":[53,91,128],"used,":[54],"has":[55],"become":[56],"<italic":[58],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[59],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">de":[60],"facto</i>":[61],"module":[62],"in":[63,158],"Conformer.":[65],"In":[66],"this":[67],"letter,":[68],"we":[69],"propose":[70],"SSCFormer":[71],"push":[73],"limit":[75],"Conformer":[78],"ASR":[81],"using":[82],"following":[84],"two":[85],"techniques:":[86],"1)":[87],"A":[88],"novel":[89],"cross-chunks":[90],"generation":[92],"method,":[93],"named":[94],"Sequential":[95],"Sampling":[96],"Chunk":[97],"(SSC)":[98],"scheme,":[99],"re-partition":[101],"chunks":[102,106],"from":[103],"regular":[104],"partitioned":[105],"facilitate":[108],"efficient":[109],"long-term":[110],"contextual":[111],"interaction":[112],"within":[113],"local":[114],"chunks.":[115],"2)The":[116],"Chunked":[117],"Causal":[118],"Convolution":[119],"(C2Conv)":[120],"is":[121],"designed":[122],"concurrently":[124],"left":[127],"and":[129,170],"context.":[132],"Evaluations":[133],"on":[134],"AISHELL-1":[135],"show":[136],"that":[137],"an":[138],"End-to-End":[139],"(E2E)":[140],"CER":[141],"5.33%":[142],"can":[143],"achieve,":[144],"which":[145],"even":[146],"outperforms":[147],"a":[148,166],"strong":[149],"time-restricted":[150],"baseline":[151],"U2.":[152],"Moreover,":[153],"MHSA":[156],"our":[159],"model":[160],"enables":[161],"it":[162],"train":[164],"with":[165,173],"large":[167],"batch":[168],"size":[169],"perform":[171],"inference":[172],"linear":[174],"complexity.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}