{"id":"https://openalex.org/W3160413945","doi":"https://doi.org/10.1109/icassp39728.2021.9415054","title":"Cif-Based Collaborative Decoding for End-to-End Contextual Speech Recognition","display_name":"Cif-Based Collaborative Decoding for End-to-End Contextual Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160413945","doi":"https://doi.org/10.1109/icassp39728.2021.9415054","mag":"3160413945"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9415054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5027728339","display_name":"Minglun Han","orcid":"https://orcid.org/0000-0002-5120-069X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"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":true,"raw_author_name":"Minglun Han","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","Institute of Automation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000236213","display_name":"Linhao Dong","orcid":null},"institutions":[{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linhao Dong","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China"],"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/A5101400153","display_name":"Shiyu Zhou","orcid":"https://orcid.org/0000-0002-6889-0316"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","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":"Shiyu Zhou","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China"],"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/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","Institute of Automation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I4210094879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027728339"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879","https://openalex.org/I4210100255","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":1.8305,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.87687301,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6528","last_page":"6532"},"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":0.9987999796867371,"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":0.9987000226974487,"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":0.8235761523246765},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7062102556228638},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6955693364143372},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6730453968048096},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5591531991958618},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5276616811752319},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.505954921245575},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5058605074882507},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4861154556274414},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.41382667422294617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4018542170524597},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32470113039016724},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3207275867462158},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18953853845596313}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8235761523246765},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7062102556228638},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6955693364143372},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6730453968048096},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5591531991958618},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5276616811752319},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.505954921245575},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5058605074882507},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4861154556274414},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.41382667422294617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4018542170524597},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32470113039016724},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3207275867462158},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18953853845596313},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9415054","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9415054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.550000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1526236009","https://openalex.org/W1828163288","https://openalex.org/W1922655562","https://openalex.org/W2327501763","https://openalex.org/W2395440424","https://openalex.org/W2403440562","https://openalex.org/W2407080277","https://openalex.org/W2577366047","https://openalex.org/W2586813637","https://openalex.org/W2753614360","https://openalex.org/W2886319145","https://openalex.org/W2888975141","https://openalex.org/W2889012072","https://openalex.org/W2889048668","https://openalex.org/W2892009249","https://openalex.org/W2898599211","https://openalex.org/W2903250132","https://openalex.org/W2913718171","https://openalex.org/W2936774411","https://openalex.org/W2937402758","https://openalex.org/W2962824709","https://openalex.org/W2972625221","https://openalex.org/W2973172693","https://openalex.org/W3016167541","https://openalex.org/W3027687786","https://openalex.org/W3041679645","https://openalex.org/W3097239815","https://openalex.org/W3097794466","https://openalex.org/W3097973766","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6640090968","https://openalex.org/W6655668998","https://openalex.org/W6713762819","https://openalex.org/W6732447497","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W3203142394","https://openalex.org/W2938107654","https://openalex.org/W3008587939","https://openalex.org/W4302615923","https://openalex.org/W1974101135","https://openalex.org/W2351061015","https://openalex.org/W2017509870"],"abstract_inverted_index":{"End-to-end":[0],"(E2E)":[1],"models":[2],"have":[3],"achieved":[4],"promising":[5],"results":[6],"on":[7,63,119,161],"multiple":[8],"speech":[9],"recognition":[10],"benchmarks,":[11],"and":[12,24,100,139],"shown":[13],"the":[14,18,21,25,46,68,102,112,115,120,159],"potential":[15],"to":[16,50,91],"become":[17],"mainstream.":[19],"However,":[20],"unified":[22],"structure":[23],"E2E":[26],"training":[27],"hamper":[28],"injecting":[29],"context":[30,86],"information":[31,53,66,99],"into":[32,67],"them":[33],"for":[34],"contextual":[35,38,52,65,76,93,98,103],"biasing.":[36],"Though":[37],"LAS":[39],"(CLAS)":[40],"gives":[41],"an":[42,84],"excellent":[43],"all-neural":[44],"solution,":[45],"degree":[47],"of":[48,114,126,137,148],"biasing":[49,77],"given":[51],"is":[54,89],"not":[55],"explicitly":[56],"controllable.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61],"focus":[62],"incorporating":[64],"continuous":[69],"integrate-and-fire":[70],"(CIF)":[71],"based":[72],"model":[73],"that":[74],"supports":[75],"in":[78],"a":[79,108,153],"more":[80],"controllable":[81],"fashion.":[82],"Specifically,":[83],"extra":[85],"processing":[87],"network":[88],"introduced":[90],"extract":[92],"embeddings,":[94],"integrate":[95],"acoustically":[96],"relevant":[97],"decode":[101],"output":[104],"distribution,":[105],"thus":[106],"forming":[107],"collaborative":[109],"decoding":[110],"with":[111,152],"decoder":[113],"CIF-based":[116],"model.":[117],"Evaluated":[118],"named":[121,141],"entity":[122,142],"rich":[123],"evaluation":[124,163],"sets":[125],"HKUST/AISHELL-2,":[127],"our":[128],"method":[129],"brings":[130],"relative":[131,140],"character":[132,143],"error":[133,144],"rate":[134,145],"(CER)":[135],"reduction":[136,147],"8.83%/21.13%":[138],"(NE-CER)":[146],"40.14%/51.50%":[149],"when":[150],"compared":[151],"strong":[154],"baseline.":[155],"Besides,":[156],"it":[157],"keeps":[158],"performance":[160],"original":[162],"set":[164],"without":[165],"degradation.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}