乐胖代购免代理版

{"id":"https://openalex.org/W4319862426","doi":"https://doi.org/10.1109/slt54892.2023.10022338","title":"Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems","display_name":"Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862426","doi":"https://doi.org/10.1109/slt54892.2023.10022338"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022338","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.00786","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057214137","display_name":"Shaan Bijwadia","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":"Shaan Bijwadia","raw_affiliation_strings":["Google, Inc."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374448","display_name":"Bo Li","orcid":"https://orcid.org/0000-0002-6711-3603"},"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":"Bo Li","raw_affiliation_strings":["Google, Inc."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","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 Sainath","raw_affiliation_strings":["Google, Inc."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460139","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-1018-4144"},"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":"Chao Zhang","raw_affiliation_strings":["Google, Inc."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","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."],"affiliations":[{"raw_affiliation_string":"Google, Inc.","institution_ids":["https://openalex.org/I1291425158"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.381,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":6,"citation_normalized_percentile":{"value":0.782619,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":92,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"310","last_page":"316"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9999,"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":0.9999,"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":0.9996,"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/T12031","display_name":"Speech and dialogue systems","score":0.9969,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.8422793}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.8422793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.71450746},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7045591},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45800164},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.42684367},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25853378}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022338","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2211.00786","pdf_url":"https://arxiv.org/pdf/2211.00786","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2211.00786","pdf_url":"https://arxiv.org/pdf/2211.00786","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":33,"referenced_works":["https://openalex.org/W10731371","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W1999454387","https://openalex.org/W2064675550","https://openalex.org/W2100844198","https://openalex.org/W2127141656","https://openalex.org/W2157331050","https://openalex.org/W2271840356","https://openalex.org/W2408468399","https://openalex.org/W2606722458","https://openalex.org/W2624871570","https://openalex.org/W2742061524","https://openalex.org/W2891367150","https://openalex.org/W2912003438","https://openalex.org/W2928941594","https://openalex.org/W2935756939","https://openalex.org/W2936774411","https://openalex.org/W2962760690","https://openalex.org/W2982031388","https://openalex.org/W3008284571","https://openalex.org/W3015383801","https://openalex.org/W3015927303","https://openalex.org/W3016010032","https://openalex.org/W3086863954","https://openalex.org/W3097777922","https://openalex.org/W3161080229","https://openalex.org/W3163203022","https://openalex.org/W3163907627","https://openalex.org/W3193786050","https://openalex.org/W3196784225","https://openalex.org/W4221147513","https://openalex.org/W4225307083"],"related_works":["https://openalex.org/W3126788496","https://openalex.org/W2981428355","https://openalex.org/W2962858469","https://openalex.org/W2559040841","https://openalex.org/W2289873871","https://openalex.org/W2149163000","https://openalex.org/W2131711534","https://openalex.org/W2041273198","https://openalex.org/W1834994814","https://openalex.org/W1599055764"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,15],"recognition":[2],"(ASR)":[3],"systems":[4],"typically":[5],"rely":[6],"on":[7,104,111],"an":[8],"external":[9],"endpointer":[10],"(EP)":[11],"model":[12,81],"to":[13,24,60,88,120],"identify":[14],"boundaries.":[16],"In":[17],"this":[18,124],"work,":[19],"we":[20],"propose":[21],"a":[22,33,53,78,112],"method":[23],"jointly":[25],"train":[26],"the":[27,47,58,63,72],"ASR":[28,48,73,106],"and":[29,95,135],"EP":[30,40,59],"tasks":[31],"in":[32,77],"single":[34,79],"end-to-end":[35],"(E2E)":[36],"multitask":[37],"model,":[38],"improving":[39],"quality":[41,99],"by":[42,130,139,154],"optionally":[43],"leveraging":[44],"information":[45],"from":[46,71],"audio":[49,64],"encoder.":[50],"We":[51,108],"introduce":[52],"\"switch\"":[54],"connection,":[55],"which":[56],"trains":[57],"consume":[61],"either":[62],"frames":[65],"directly":[66],"or":[67],"low-level":[68],"latent":[69],"representations":[70],"model.":[74],"This":[75],"results":[76,110],"E2E":[80],"that":[82],"can":[83],"be":[84],"used":[85],"during":[86],"inference":[87],"perform":[89],"frame":[90],"filtering":[91],"at":[92],"low":[93],"cost,":[94],"also":[96],"make":[97],"high":[98],"end-of-query":[100],"(EOQ)":[101],"predictions":[102],"based":[103],"ongoing":[105],"computation.":[107],"present":[109],"voice":[113],"search":[114],"test":[115],"set":[116],"showing":[117],"that,":[118],"compared":[119],"separate":[121],"single-task":[122],"models,":[123],"approach":[125],"reduces":[126],"median":[127],"endpoint":[128],"latency":[129,138],"120":[131],"ms":[132,141],"(30.8%":[133],"reduction),":[134,143],"90th":[136],"percentile":[137],"170":[140],"(23.0%":[142],"without":[144],"regressing":[145],"word":[146],"error":[147],"rate.":[148],"For":[149],"continuous":[150],"recognition,":[151],"WER":[152],"improves":[153],"10.6%":[155],"(relative).":[156]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4319862426","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5}],"updated_date":"2025-01-19T14:21:54.480193","created_date":"2023-02-11"}