{"id":"https://openalex.org/W3161080229","doi":"https://doi.org/10.1109/icassp39728.2021.9413613","title":"Preventing Early Endpointing for Online Automatic Speech Recognition","display_name":"Preventing Early Endpointing for Online Automatic Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161080229","doi":"https://doi.org/10.1109/icassp39728.2021.9413613","mag":"3161080229"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413613","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/A5018178902","display_name":"Yingzhu Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG","US"],"is_corresponding":true,"raw_author_name":"Yingzhu Zhao","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group","Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102306089","display_name":"Chongjia Ni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chongjia Ni","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113828649","display_name":"Cheung-Chi Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheung-Chi Leung","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005443526","display_name":"Shafiq Joty","orcid":"https://orcid.org/0000-0002-9222-2641"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shafiq Joty","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Machine Intelligence Technology, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence Technology, Alibaba Group","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5018178902"],"corresponding_institution_ids":["https://openalex.org/I172675005","https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67395019,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6813","last_page":"6817"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8380125761032104},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.8255822658538818},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7642045617103577},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6778979301452637},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6006958484649658},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.492787629365921},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46358346939086914},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4614744186401367},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45762714743614197},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4437390863895416},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4423767626285553},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.42288467288017273},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3914841115474701},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3232117295265198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8380125761032104},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8255822658538818},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7642045617103577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6778979301452637},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6006958484649658},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.492787629365921},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46358346939086914},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4614744186401367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45762714743614197},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4437390863895416},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4423767626285553},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.42288467288017273},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3914841115474701},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3232117295265198},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413613","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413613","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1828163288","https://openalex.org/W2125838338","https://openalex.org/W2143612262","https://openalex.org/W2147207799","https://openalex.org/W2605141709","https://openalex.org/W2625979394","https://openalex.org/W2892009249","https://openalex.org/W2892300106","https://openalex.org/W2935756939","https://openalex.org/W2936123380","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2964272710","https://openalex.org/W2968297680","https://openalex.org/W2972977747","https://openalex.org/W2995404354","https://openalex.org/W3015457435","https://openalex.org/W3015671919","https://openalex.org/W3015927303","https://openalex.org/W3018242354","https://openalex.org/W3096888553","https://openalex.org/W3126409997","https://openalex.org/W3171641923","https://openalex.org/W4294619417","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6735706088","https://openalex.org/W6747158283","https://openalex.org/W6754299077","https://openalex.org/W6767057552"],"related_works":["https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2069501481","https://openalex.org/W3126788496","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W2103239478"],"abstract_inverted_index":{"With":[0],"the":[1,53,58,65,75,87,91,103,106,111,130,145,149,179,183,190],"recent":[2],"development":[3],"of":[4,90,105,139,193],"end-to-end":[5,25],"models":[6,18,26],"in":[7,15,42],"speech":[8,21,29],"recognition,":[9],"there":[10],"have":[11],"been":[12],"more":[13],"interests":[14],"adapting":[16],"these":[17],"for":[19,27],"online":[20,28],"recognition.":[22],"However,":[23],"using":[24],"recognition":[30],"is":[31,98],"known":[32],"to":[33,51,73,85,100,109,113,115],"suffer":[34],"from":[35,57,80,147],"an":[36],"early":[37,54,88],"endpointing":[38,55],"problem,":[39],"which":[40,70,187],"brings":[41,173],"many":[43],"deletion":[44],"errors.":[45],"In":[46],"this":[47],"paper,":[48],"we":[49,62,82],"propose":[50],"address":[52],"problem":[56],"gradient":[59,104],"perspective.":[60],"Specifically,":[61],"leverage":[63],"on":[64,136,166],"recently":[66],"proposed":[67,72,131],"ScaleGrad":[68],"technique,":[69],"was":[71],"mitigate":[74],"text":[76],"degeneration":[77],"issue.":[78],"Different":[79],"ScaleGrad,":[81],"adapt":[83],"it":[84,142,157],"discourage":[86],"generation":[89,191],"end-of-sentence":[92],"(<eos>)":[93],"token.":[94,195],"A":[95],"scaling":[96],"term":[97],"added":[99],"directly":[101,188],"maneuver":[102],"training":[107,185],"loss":[108],"encourage":[110],"model":[112,172],"learn":[114],"keep":[116],"generating":[117],"non-<eos>":[118],"tokens.":[119],"Compared":[120],"with":[121,153,162],"previous":[122],"approaches":[123],"such":[124],"as":[125],"voice-activity-detection":[126],"and":[127,141,181],"end-of-query":[128],"detection,":[129],"method":[132,186],"does":[133],"not":[134],"rely":[135],"various":[137],"types":[138],"silence,":[140],"also":[143],"saves":[144],"trouble":[146],"obtaining":[148],"ground":[150],"truth":[151],"endpoint":[152],"forced":[154],"alignment.":[155],"Nevertheless,":[156],"can":[158],"be":[159],"jointly":[160],"applied":[161],"other":[163],"techniques.":[164],"Experiments":[165],"AISHELL-1":[167],"dataset":[168],"show":[169],"that":[170],"our":[171],"relative":[174],"5.4%-10.1%":[175],"CER":[176],"reductions":[177],"over":[178],"baseline,":[180],"surpasses":[182],"unlikelihood":[184],"reduces":[189],"probability":[192],"<eos>":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}