乐胖代购免代理版

{"id":"https://openalex.org/W4319862468","doi":"https://doi.org/10.1109/slt54892.2023.10023346","title":"A Truly Multilingual First Pass and Monolingual Second Pass Streaming on-Device ASR System","display_name":"A Truly Multilingual First Pass and Monolingual Second Pass Streaming on-Device ASR System","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862468","doi":"https://doi.org/10.1109/slt54892.2023.10023346"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023346","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_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":["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/A5060420622","display_name":"Sepand Mavandadi","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":"Sepand Mavandadi","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","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 LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460199","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0002-7167-0840"},"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 LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068291585","display_name":"Brian Farris","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":"Brian Farris","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","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 LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032931723","display_name":"Trevor Strohman","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":"Trevor Strohman","raw_affiliation_strings":["Google LLC, USA"],"affiliations":[{"raw_affiliation_string":"Google LLC, USA","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":0.824,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.999754,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":78,"max":84},"biblio":{"volume":"abs 1706 3762","issue":null,"first_page":"838","last_page":"845"},"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":0.9994,"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":0.9974,"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/word-error-rate","display_name":"Word error rate","score":0.49267536},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription","score":0.45995322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8523895},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7447285},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6476047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6239503},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.53922564},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49267536},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.45995322},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45671028},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.432815},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42191604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41666707},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11432478},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.069761366},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10023346","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_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}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":39,"referenced_works":["https://openalex.org/W1586532344","https://openalex.org/W1828163288","https://openalex.org/W2143612262","https://openalex.org/W2597655663","https://openalex.org/W2786835190","https://openalex.org/W2919115771","https://openalex.org/W2928941594","https://openalex.org/W2931364255","https://openalex.org/W2962704885","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963414781","https://openalex.org/W2964309797","https://openalex.org/W2971840980","https://openalex.org/W3008434450","https://openalex.org/W3015995734","https://openalex.org/W3016234571","https://openalex.org/W3095311338","https://openalex.org/W3096032230","https://openalex.org/W3097777922","https://openalex.org/W3156258992","https://openalex.org/W3156323585","https://openalex.org/W3160766462","https://openalex.org/W3163169798","https://openalex.org/W3163203022","https://openalex.org/W3163865502","https://openalex.org/W3163907627","https://openalex.org/W3178647810","https://openalex.org/W3197976839","https://openalex.org/W3198442913","https://openalex.org/W3211278025","https://openalex.org/W4225295099","https://openalex.org/W4225307083","https://openalex.org/W4287726212","https://openalex.org/W4293569541","https://openalex.org/W4296069150","https://openalex.org/W4297841565","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W767271433","https://openalex.org/W4386907265","https://openalex.org/W4290708361","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W2118730790","https://openalex.org/W2058752985","https://openalex.org/W2050138804","https://openalex.org/W1566315437"],"abstract_inverted_index":{"Automatic":[0],"speech":[1,62],"recognition":[2,86],"(ASR)":[3],"systems":[4],"need":[5],"to":[6,19,83,119,127],"be":[7,20,128],"accurate,":[8],"have":[9],"low":[10],"latency,":[11],"and":[12,42,106],"effectively":[13],"handle":[14],"language":[15,65,78,91],"switching":[16],"in":[17,136],"order":[18],"useful":[21],"for":[22,71],"the":[23,26,51,85,137],"60%":[24],"of":[25,139],"world":[27],"population":[28],"that":[29,97],"speaks":[30],"more":[31],"than":[32],"one":[33],"language.":[34],"Thus,":[35],"we":[36,95],"propose":[37],"a":[38,77,89,98],"truly":[39],"multilingual":[40,61],"first-pass":[41,59],"monolingual":[43,120],"second-pass":[44,75],"streaming":[45,58],"on-device":[46],"ASR":[47],"system":[48,99],"based":[49],"on":[50],"recently":[52],"developed":[53],"Cascaded":[54],"Encoders":[55],"model.":[56],"The":[57,74],"recognizes":[60],"without":[63],"needing":[64],"information,":[66],"providing":[67],"real-time":[68],"transcription,":[69],"even":[70],"code-switching":[72],"speech.":[73],"uses":[76],"dependent":[79],"right":[80],"context":[81],"encoder":[82,103],"improve":[84],"accuracy.":[87],"On":[88],"9":[90],"Voice":[92],"Search":[93],"task,":[94],"find":[96],"combining":[100],"shared":[101],"causal":[102],"with":[104],"decoders":[105],"non-causal":[107],"encoders":[108],"replicated":[109],"per-language":[110],"reduces":[111],"word":[112],"error":[113],"rate":[114],"(WER)":[115],"by":[116],"4.4%":[117],"relative":[118],"baselines.":[121],"We":[122],"further":[123],"show":[124],"this":[125],"design":[126],"parameter":[129],"efficient,":[130],"outperforming":[131],"other":[132],"architectures":[133],"when":[134],"matched":[135],"number":[138],"parameters.":[140]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4319862468","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-01-02T11:22:48.024889","created_date":"2023-02-11"}