{"id":"https://openalex.org/W2903250132","doi":"https://doi.org/10.1109/icassp.2019.8683573","title":"End-to-end Contextual Speech Recognition Using Class Language Models and a Token Passing Decoder","display_name":"End-to-end Contextual Speech Recognition Using Class Language Models and a Token Passing Decoder","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2903250132","doi":"https://doi.org/10.1109/icassp.2019.8683573","mag":"2903250132"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683573","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1812.02142","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"institutions":[{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]},{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["Facebook, Menlo Park, CA, USA"],"affiliations":[{"raw_affiliation_string":"Facebook, Menlo Park, CA, USA","institution_ids":["https://openalex.org/I4210099336","https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112701957","display_name":"Mahaveer Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahaveer Jain","raw_affiliation_strings":["Facebook, Menlo Park, CA, 94025, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook, Menlo Park, CA, 94025, USA#TAB#","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339989","display_name":"Yongqiang Wang","orcid":"https://orcid.org/0000-0002-8600-0276"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongqiang Wang","raw_affiliation_strings":["Facebook, Menlo Park, CA, 94025, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook, Menlo Park, CA, 94025, USA#TAB#","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael L. Seltzer","raw_affiliation_strings":["Facebook, Menlo Park, CA, 94025, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook, Menlo Park, CA, 94025, USA#TAB#","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047073253","display_name":"Christian Fuegen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Fuegen","raw_affiliation_strings":["Facebook, Menlo Park, CA, 94025, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Facebook, Menlo Park, CA, 94025, USA#TAB#","institution_ids":["https://openalex.org/I4210114444","https://openalex.org/I4210099336"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.25,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":42,"citation_normalized_percentile":{"value":0.999907,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6186","last_page":"6190"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition Technology","score":1.0,"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 Technology","score":1.0,"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":"Statistical Machine Translation and Natural Language Processing","score":0.9995,"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":"Natural Language Processing","score":0.9985,"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-speech-recognition","display_name":"End-to-End Speech Recognition","score":0.69554},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6117877},{"id":"https://openalex.org/keywords/automatic-speech-recognition","display_name":"Automatic Speech Recognition","score":0.585192},{"id":"https://openalex.org/keywords/sequence-to-sequence-learning","display_name":"Sequence-to-Sequence Learning","score":0.558587},{"id":"https://openalex.org/keywords/language-modeling","display_name":"Language Modeling","score":0.553679},{"id":"https://openalex.org/keywords/statistical-language-modeling","display_name":"Statistical Language Modeling","score":0.548327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8702548},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.72837204},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.68097204},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6704237},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.61624956},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6157413},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6117877},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.59481263},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5846964},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5537452},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.47979075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46373713},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4237454},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.356695},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08322662},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/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}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683573","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1812.02142","pdf_url":"https://arxiv.org/pdf/1812.02142","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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/1812.02142","pdf_url":"https://arxiv.org/pdf/1812.02142","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":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":[{"score":0.56,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":27,"referenced_works":["https://openalex.org/W2046932483","https://openalex.org/W2160815625","https://openalex.org/W2293634267","https://openalex.org/W2293829681","https://openalex.org/W2395440424","https://openalex.org/W2406494896","https://openalex.org/W2507132449","https://openalex.org/W2537374808","https://openalex.org/W2545177271","https://openalex.org/W2548332580","https://openalex.org/W2584407414","https://openalex.org/W27187656","https://openalex.org/W2756151591","https://openalex.org/W2761116321","https://openalex.org/W2766219058","https://openalex.org/W2787663903","https://openalex.org/W2886319145","https://openalex.org/W2887908873","https://openalex.org/W2888930363","https://openalex.org/W2889012072","https://openalex.org/W2889152503","https://openalex.org/W2962780374","https://openalex.org/W2962961016","https://openalex.org/W2963240019","https://openalex.org/W2963380677","https://openalex.org/W3099832538","https://openalex.org/W47415966"],"related_works":["https://openalex.org/W50892825","https://openalex.org/W4389471172","https://openalex.org/W4290708361","https://openalex.org/W4221142855","https://openalex.org/W2944691285","https://openalex.org/W26527944","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W2129812225","https://openalex.org/W2050138804"],"abstract_inverted_index":{"End-to-end":[0],"modeling":[1],"(E2E)":[2],"of":[3,12,74,104,170],"automatic":[4],"speech":[5,15,49],"recognition":[6,16,152],"(ASR)":[7],"blends":[8],"all":[9],"the":[10,26,29,69,72,127,146,155,163,171],"components":[11],"a":[13,19,101,113,178],"traditional":[14],"system":[17,129],"into":[18],"single,":[20],"unified":[21,30],"model.":[22],"Although":[23],"it":[24,177],"simplifies":[25],"ASR":[27,134,148,157],"systems,":[28],"model":[31],"is":[32,52,61],"hard":[33],"to":[34,81,98,100],"adapt":[35],"when":[36],"training":[37],"and":[38,107,132,136],"testing":[39],"data":[40],"mismatches.":[41],"In":[42],"this":[43,96],"work,":[44],"we":[45,79,111],"focus":[46],"on":[47,130],"contextual":[48,59,75,133,147],"recognition,":[50],"which":[51],"particularly":[53],"challenging":[54],"for":[55,122,145,154,181],"E2E":[56,123,182],"models":[57,85],"because":[58],"information":[60,76,91],"only":[62],"available":[63],"in":[64,71],"inference":[65],"time.":[66],"To":[67,94],"improve":[68],"performance":[70,153],"presence":[73],"during":[77,92],"training,":[78],"propose":[80,112],"use":[82],"class-based":[83],"language":[84],"(CLM)":[86],"that":[87,162],"can":[88],"populate":[89],"context-dependent":[90],"inference.":[93],"enable":[95],"approach":[97],"scale":[99],"large":[102],"number":[103],"class":[105],"members":[106],"minimize":[108],"search":[109],"errors,":[110],"token":[114,120],"passing":[115],"algorithm":[116],"with":[117],"an":[118],"efficient":[119],"recombination":[121],"systems.":[124],"We":[125,159],"evaluate":[126],"proposed":[128,164],"general":[131,156],"tasks,":[135,175],"achieve":[137],"relative":[138],"62%":[139],"Word":[140],"Error":[141],"Rate":[142],"(WER)":[143],"reduction":[144],"task":[149],"without":[150,168],"hurting":[151],"task.":[158],"also":[160],"show":[161],"method":[165],"performs":[166],"well":[167],"modification":[169],"decoding":[172],"hyper-parameters":[173],"across":[174],"making":[176],"desirable":[179],"solution":[180],"ASR.":[183]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2903250132","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":6}],"updated_date":"2024-11-30T00:11:55.755833","created_date":"2018-12-11"}
