{"id":"https://openalex.org/W4360930497","doi":"https://doi.org/10.1109/lsp.2023.3261662","title":"A CIF-Based Speech Segmentation Method for Streaming E2E ASR","display_name":"A CIF-Based Speech Segmentation Method for Streaming E2E ASR","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4360930497","doi":"https://doi.org/10.1109/lsp.2023.3261662"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2023.3261662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3261662","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/A5008475151","display_name":"Yuchun Shu","orcid":"https://orcid.org/0000-0002-4375-1002"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuchun Shu","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088820402","display_name":"Haoneng Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I3087508612","display_name":"Pride Foundation","ror":"https://ror.org/05tewmz75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3087508612"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Haoneng Luo","raw_affiliation_strings":["reside in, Hangzhou, China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"reside in, Hangzhou, China","institution_ids":["https://openalex.org/I3087508612"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I3087508612","display_name":"Pride Foundation","ror":"https://ror.org/05tewmz75","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I3087508612"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["reside in, Hangzhou, China","Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"reside in, Hangzhou, China","institution_ids":["https://openalex.org/I3087508612"]},{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101745213","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017251198","display_name":"Jianwu Dang","orcid":"https://orcid.org/0000-0002-9237-4821"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Key Laboratory of Cognitive Computing and Application, College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008475151"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":1.2205,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.82639295,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"30","issue":null,"first_page":"344","last_page":"348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9983000159263611,"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":0.9836000204086304,"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":0.8742513060569763},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.8385884165763855},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7018044590950012},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5781590938568115},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5658392906188965},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.528462827205658},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4932538866996765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45051637291908264},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38070613145828247},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.35804349184036255},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06140047311782837}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8742513060569763},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8385884165763855},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7018044590950012},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5781590938568115},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5658392906188965},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.528462827205658},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4932538866996765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45051637291908264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38070613145828247},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.35804349184036255},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06140047311782837},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2023.3261662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2023.3261662","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/G7732325329","display_name":null,"funder_award_id":"62176182","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":40,"referenced_works":["https://openalex.org/W1563939609","https://openalex.org/W1920942766","https://openalex.org/W2100844198","https://openalex.org/W2127141656","https://openalex.org/W2631415506","https://openalex.org/W2790412906","https://openalex.org/W2891367150","https://openalex.org/W2935756939","https://openalex.org/W2973122799","https://openalex.org/W3007073761","https://openalex.org/W3013690751","https://openalex.org/W3015383801","https://openalex.org/W3015927303","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3016167541","https://openalex.org/W3081958278","https://openalex.org/W3092970820","https://openalex.org/W3095687747","https://openalex.org/W3096123040","https://openalex.org/W3097580812","https://openalex.org/W3160766462","https://openalex.org/W3162665866","https://openalex.org/W3163203022","https://openalex.org/W3196784225","https://openalex.org/W3197478142","https://openalex.org/W3203407300","https://openalex.org/W4221147513","https://openalex.org/W4224457787","https://openalex.org/W4283067311","https://openalex.org/W4297841343","https://openalex.org/W4307534229","https://openalex.org/W4319862426","https://openalex.org/W4372349408","https://openalex.org/W4376457029","https://openalex.org/W4385245566","https://openalex.org/W6640172592","https://openalex.org/W6784721964","https://openalex.org/W6790121257","https://openalex.org/W6846573642"],"related_works":["https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W2052688117","https://openalex.org/W2103239478","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340"],"abstract_inverted_index":{"Long":[0],"utterances":[1],"segmentation":[2,21,45,97],"is":[3,79],"crucial":[4],"in":[5,126],"end-to-end":[6],"(E2E)":[7],"streaming":[8,48],"automatic":[9],"speech":[10,44],"recognition":[11],"(ASR).":[12],"However,":[13],"commonly":[14],"used":[15,70],"voice":[16],"activity":[17],"detection(VAD)-based":[18],"and":[19,28,35,63,110,128,144],"fixed-length":[20],"methods":[22],"may":[23],"lead":[24],"to":[25,51,92],"long":[26],"segments":[27],"semantic":[29,135],"incompleteness,":[30],"affecting":[31],"the":[32,53,57,64,82,101,107,124,129],"user":[33],"experience":[34],"ASR":[36,50,91],"performance.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"a":[43,94],"method":[46,103,120],"for":[47,71,98],"E2E":[49],"solve":[52],"above":[54],"issues.":[55],"Both":[56],"decoder's":[58,76],"dependence":[59,77],"on":[60],"acoustic":[61],"information":[62,78],"human":[65],"average":[66],"breath":[67],"frequency":[68],"are":[69,149],"judging":[72],"segment":[73,130],"boundaries.":[74],"Frame-level":[75],"provided":[80],"by":[81],"Continuous":[83],"Integrate-and-Fire":[84],"(CIF)":[85],"predictor,":[86],"which":[87],"optimizes":[88],"jointly":[89],"with":[90,138],"guarantee":[93],"more":[95],"suitable":[96],"ASR.":[99],"Besides,":[100],"proposed":[102],"does":[104],"not":[105],"increase":[106],"model":[108],"parameters":[109],"real-time":[111],"factor":[112],"(RTF).":[113],"The":[114],"experimental":[115],"results":[116],"show":[117],"that":[118],"our":[119],"can":[121],"accurately":[122],"detect":[123],"pauses":[125],"speech,":[127],"usually":[131],"contains":[132],"relatively":[133,148],"complete":[134],"information.":[136],"Compared":[137],"VAD-based":[139],"segmentation,":[140],"53.5%":[141],"latency":[142],"reduction":[143,147],"3.7%":[145],"CER":[146],"achieved.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}