{"id":"https://openalex.org/W2935756939","doi":"https://doi.org/10.1109/icassp.2019.8683109","title":"Joint Endpointing and Decoding with End-to-end Models","display_name":"Joint Endpointing and Decoding with End-to-end Models","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2935756939","doi":"https://doi.org/10.1109/icassp.2019.8683109","mag":"2935756939"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5001306222","display_name":"Shuo-Yiin Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo-Yiin Chang","raw_affiliation_strings":["Google Inc, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rohit Prabhavalkar","raw_affiliation_strings":["Google Inc, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101319167","display_name":"Yanzhang He","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhang He","raw_affiliation_strings":["Google Inc, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google Inc, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050938071","display_name":"Gabor Simko","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gabor Simko","raw_affiliation_strings":["Google Inc, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc, U.S.A","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5626","last_page":"5630"},"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":0.8117566108703613},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7345738410949707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7041475772857666},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6382526159286499},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5916642546653748},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5853111147880554},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5542237758636475},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5496403574943542},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5253669023513794},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4810769557952881},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4506518840789795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3618099093437195},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15608817338943481},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10642880201339722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8117566108703613},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7345738410949707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7041475772857666},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6382526159286499},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5916642546653748},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5853111147880554},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5542237758636475},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5496403574943542},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5253669023513794},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4810769557952881},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4506518840789795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3618099093437195},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15608817338943481},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10642880201339722},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1536583098","https://openalex.org/W1600744878","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W2064675550","https://openalex.org/W2271840356","https://openalex.org/W2295098554","https://openalex.org/W2513345070","https://openalex.org/W2526425061","https://openalex.org/W2617258110","https://openalex.org/W2625979394","https://openalex.org/W2742061524","https://openalex.org/W2891367150","https://openalex.org/W2892300106","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963414781","https://openalex.org/W6635768407","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6694517276","https://openalex.org/W6697089127","https://openalex.org/W6728030952","https://openalex.org/W6747398299","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2916997151","https://openalex.org/W2949174760","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048"],"abstract_inverted_index":{"The":[0],"tradeoff":[1],"between":[2],"word":[3],"error":[4],"rate":[5],"(WER)":[6],"and":[7,25,52,57,60,86,124],"latency":[8,159],"is":[9],"very":[10],"important":[11],"for":[12],"streaming":[13],"automatic":[14],"speech":[15],"recognition":[16,123],"(ASR)":[17],"applications.":[18],"We":[19,112],"want":[20],"the":[21,27,49,74,83,100,109,141,174],"system":[22],"to":[23,106,114,168],"endpoint":[24],"close":[26],"microphone":[28],"as":[29,31,127],"quickly":[30],"possible,":[32],"without":[33],"degrading":[34],"WER.":[35],"Conventional":[36],"ASR":[37],"systems":[38],"rely":[39],"on":[40],"a":[41,64,68,89,132,149,163,170],"separately":[42],"trained":[43],"endpointing":[44,110,125],"module,":[45],"which":[46,81,120],"interacts":[47],"with":[48,73,108,148,173],"acoustic,":[50],"pronunciation":[51],"language":[53],"model":[54,105,118],"(AM,":[55],"PM,":[56],"LM)":[58],"components,":[59],"can":[61],"result":[62],"in":[63,93,153],"higher":[65],"WER":[66],"or":[67],"larger":[69],"latency.":[70],"In":[71],"going":[72],"all-neural":[75],"spirit":[76],"of":[77,143,165],"end-to-end":[78],"(E2E)":[79],"models,":[80],"fold":[82],"AM,":[84],"PM":[85],"LM":[87],"into":[88,102],"single":[90],"neural":[91],"network,":[92],"this":[94,103,115],"work":[95],"we":[96,138],"look":[97],"at":[98],"folding":[99],"endpointer":[101,151,172],"E2E":[104,129,146,175],"assist":[107],"task.":[111],"refer":[113],"jointly":[116],"optimized":[117],"-":[119,126],"performs":[121],"both":[122],"an":[128,145],"enpointer.":[130],"On":[131],"large":[133],"vocabulary":[134],"Voice":[135],"Search":[136],"task,":[137],"show":[139],"that":[140],"combination":[142],"such":[144],"endpoiner":[147],"conventional":[150],"results":[152],"no":[154],"quality":[155],"degradation,":[156],"while":[157],"reducing":[158],"by":[160],"more":[161],"than":[162],"factor":[164],"2":[166],"compared":[167],"using":[169],"separate":[171],"model.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":11}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}