{"id":"https://openalex.org/W4372266509","doi":"https://doi.org/10.1109/icassp49357.2023.10096155","title":"Towards Accurate and Real-Time End-of-Speech Estimation","display_name":"Towards Accurate and Real-Time End-of-Speech Estimation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266509","doi":"https://doi.org/10.1109/icassp49357.2023.10096155"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096155","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5102714797","display_name":"Yifeng Fan","orcid":"https://orcid.org/0000-0002-4434-0432"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yifeng Fan","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082491203","display_name":"Colin Vaz","orcid":"https://orcid.org/0000-0002-5709-7953"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colin Vaz","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017672130","display_name":"Di He","orcid":"https://orcid.org/0009-0008-5025-7062"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di He","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006131416","display_name":"Jahn Heymann","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jahn Heymann","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085746637","display_name":"Viet Anh Trinh","orcid":"https://orcid.org/0000-0002-1660-6627"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viet Anh Trinh","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442950","display_name":"Zhe Zhang","orcid":"https://orcid.org/0000-0001-8407-3167"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Zhang","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060593241","display_name":"Venkatesh Ravichandran","orcid":"https://orcid.org/0009-0001-7214-2919"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkatesh Ravichandran","raw_affiliation_strings":["Amazon Alexa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102714797"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.1688,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53023111,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9994999766349792,"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":0.8045992851257324},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6475276947021484},{"id":"https://openalex.org/keywords/timestamp","display_name":"Timestamp","score":0.6166105270385742},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5861333012580872},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5740699768066406},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5276424288749695},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49293971061706543},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4825941324234009},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4505404531955719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3585491180419922},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33379095792770386},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.15308037400245667},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10148939490318298}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8045992851257324},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6475276947021484},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.6166105270385742},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5861333012580872},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5740699768066406},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5276424288749695},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49293971061706543},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4825941324234009},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4505404531955719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3585491180419922},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33379095792770386},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.15308037400245667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10148939490318298},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096155","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096155","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1991133427","https://openalex.org/W2100844198","https://openalex.org/W2327501763","https://openalex.org/W2742061524","https://openalex.org/W2891367150","https://openalex.org/W2935756939","https://openalex.org/W3015927303","https://openalex.org/W3096524176","https://openalex.org/W4221147513","https://openalex.org/W4301410255","https://openalex.org/W6631362777","https://openalex.org/W6675365184"],"related_works":["https://openalex.org/W2060561905","https://openalex.org/W1417711376","https://openalex.org/W2032260263","https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W1986883493","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W2469862403","https://openalex.org/W4392306477"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,124],"variant":[3],"of":[4,133],"the":[5,18,30,33,45,60,81,106,130,134,141],"endpoint":[6],"(EP)":[7],"detection":[8],"problem":[9],"in":[10,53],"automatic":[11],"speech":[12],"recognition":[13],"(ASR),":[14],"which":[15,96],"we":[16,69,87,121],"call":[17],"end-of-speech":[19],"(EOS)":[20],"estimation.":[21],"Given":[22],"an":[23,71,98],"utterance,":[24],"EOS":[25,49,99],"estimation":[26,50,100,107],"aims":[27],"to":[28,43,59,89,102,114,139],"identify":[29],"timestamp":[31],"when":[32],"utterance":[34],"waveform":[35],"has":[36],"fully":[37],"decayed":[38],"and":[39,63,73,105],"is":[40,51,109],"then":[41],"used":[42],"measure":[44],"EP":[46],"latency.":[47],"Accurate":[48],"difficult":[52],"large-scale":[54],"streaming":[55],"audio":[56],"scenarios":[57],"due":[58],"hefty":[61],"traffic":[62],"hardware":[64],"limitations.":[65],"To":[66],"this":[67],"end,":[68],"develop":[70],"efficient":[72],"accurate":[74],"framework":[75],"by":[76,111,128],"performing":[77],"force":[78],"alignment":[79],"on":[80,116],"1-best":[82],"ASR":[83,103],"hypothesis.":[84],"In":[85,119],"particular,":[86],"propose":[88],"use":[90],"binarized":[91],"states":[92],"sequences":[93],"for":[94],"alignment,":[95],"yields":[97],"robust":[101],"hypothesis,":[104],"error":[108,126],"reduced":[110],"28%":[112],"compared":[113],"aligning":[115],"phoneme":[117],"states.":[118],"addition,":[120],"further":[122],"observe":[123],"30%":[125],"reduction":[127],"applying":[129],"intermediate-stage":[131],"embeddings":[132],"encoder":[135],"as":[136],"additional":[137],"features":[138],"compute":[140],"binary":[142],"probabilities.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}
