{"id":"https://openalex.org/W4283741996","doi":"https://doi.org/10.21437/interspeech.2022-10954","title":"On the Prediction Network Architecture in RNN-T for ASR","display_name":"On the Prediction Network Architecture in RNN-T for ASR","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283741996","doi":"https://doi.org/10.21437/interspeech.2022-10954"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10954","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10954","pdf_url":"https://www.isca-archive.org/interspeech_2022/albesano22_interspeech.pdf","source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.isca-archive.org/interspeech_2022/albesano22_interspeech.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014480570","display_name":"D. Albesano","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dario Albesano","raw_affiliation_strings":["Nuance Communications, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019869698","display_name":"Jes\u00fas Andr\u00e9s-Ferrer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Andr\u00e9s-Ferrer","raw_affiliation_strings":["Nuance Communications, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027968457","display_name":"Nicola Ferri","orcid":"https://orcid.org/0000-0001-8898-7441"},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicola Ferri","raw_affiliation_strings":["Nuance Communications, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109588257","display_name":"Puming Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Puming Zhan","raw_affiliation_strings":["Nuance Communications, Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications, Inc","institution_ids":["https://openalex.org/I4210125787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210125787"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2093","last_page":"2097"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9933000206947327,"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/T10863","display_name":"Voice and Speech Disorders","score":0.972100019454956,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7636877298355103},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6107151508331299},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.539391279220581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40610411763191223},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2707669138908386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7636877298355103},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6107151508331299},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.539391279220581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40610411763191223},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2707669138908386},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10954","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10954","pdf_url":"https://www.isca-archive.org/interspeech_2022/albesano22_interspeech.pdf","source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2022-10954","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10954","pdf_url":"https://www.isca-archive.org/interspeech_2022/albesano22_interspeech.pdf","source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283741996.pdf","grobid_xml":"https://content.openalex.org/works/W4283741996.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1828163288","https://openalex.org/W2407080277","https://openalex.org/W2746192915","https://openalex.org/W2936774411","https://openalex.org/W3008174054","https://openalex.org/W3015686596","https://openalex.org/W3016010032","https://openalex.org/W3016234571","https://openalex.org/W3092122846","https://openalex.org/W3093579165","https://openalex.org/W3095173472","https://openalex.org/W3097777922","https://openalex.org/W3161375121","https://openalex.org/W3161532853","https://openalex.org/W3161873870","https://openalex.org/W3162665866","https://openalex.org/W3163560333","https://openalex.org/W4287989347","https://openalex.org/W4288088457","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2902723393","https://openalex.org/W2800726910","https://openalex.org/W3107474891","https://openalex.org/W2383828164","https://openalex.org/W396164270","https://openalex.org/W2382623646","https://openalex.org/W2972850838","https://openalex.org/W2148971169","https://openalex.org/W2782968911","https://openalex.org/W2901346193"],"abstract_inverted_index":{"RNN-T":[0,41],"models":[1],"have":[2],"gained":[3],"popularity":[4],"in":[5,9,20,119,137],"the":[6,117],"literature":[7],"and":[8,16,39,56,62,74,124],"commercial":[10],"systems":[11],"because":[12],"of":[13,18,46,139,165],"their":[14],"competitiveness":[15],"capability":[17],"operating":[19],"online":[21,75,121],"streaming":[22,76,122],"mode.In":[23],"this":[24],"work,":[25],"we":[26,105,142],"conduct":[27],"an":[28,63,163],"extensive":[29],"study":[30,69],"comparing":[31],"several":[32],"prediction":[33,47,96,110,158],"network":[34,97,111,159],"architectures":[35,127],"for":[36],"both":[37,71],"monotonic":[38],"original":[40],"models.We":[42],"compare":[43],"4":[44],"types":[45],"networks":[48],"based":[49],"on":[50,60],"a":[51,107],"common":[52],"state-of-the-art":[53],"Conformer":[54,100],"encoder":[55],"report":[57],"results":[58,84],"obtained":[59,143],"Librispeech":[61],"internal":[64],"medical":[65],"conversation":[66],"data":[67],"set.Our":[68],"covers":[70],"offline":[72],"batch-mode":[73],"scenarios.In":[77],"contrast":[78],"to":[79,145,152],"some":[80,133],"previous":[81,140],"works,":[82],"our":[83,103,120,153],"show":[85],"that":[86,115],"Transformer":[87],"does":[88],"not":[89],"always":[90],"outperform":[91],"LSTM":[92,154],"when":[93],"used":[94],"as":[95],"along":[98],"with":[99,132],"encoder.Inspired":[101],"by":[102,161],"scoreboard,":[104],"propose":[106],"new":[108],"simple":[109],"architecture,":[112],"N":[113],"-Concat,":[114],"outperforms":[116],"others":[118],"benchmark.Transformer":[123],"n-gram":[125],"reduced":[126],"perform":[128],"very":[129],"similarly":[130],"yet":[131],"important":[134],"distinct":[135],"behaviour":[136],"terms":[138],"context.Overall":[141],"up":[144],"4.1":[146],"%":[147],"relative":[148],"WER":[149],"improvement":[150],"compared":[151],"baseline,":[155],"while":[156],"reducing":[157],"parameters":[160],"nearly":[162],"order":[164],"magnitude":[166],"(8.4":[167],"times).":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}