{"id":"https://openalex.org/W4296068782","doi":"https://doi.org/10.21437/interspeech.2022-733","title":"Conformer with dual-mode chunked attention for joint online and offline ASR","display_name":"Conformer with dual-mode chunked attention for joint online and offline ASR","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068782","doi":"https://doi.org/10.21437/interspeech.2022-733"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-733","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-733","pdf_url":null,"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":null,"license_id":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016747567","display_name":"Felix Weninger","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":true,"raw_author_name":"Felix Weninger","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/A5050683447","display_name":"Marco Gaudesi","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":"Marco Gaudesi","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/A5072998035","display_name":"Md Akmal Haidar","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":"Md Akmal Haidar","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":"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":"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":["https://openalex.org/A5016747567"],"corresponding_institution_ids":["https://openalex.org/I4210125787"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9402999877929688,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10662","display_name":"Ultrasonics and Acoustic Wave Propagation","score":0.9402999877929688,"subfield":{"id":"https://openalex.org/subfields/2211","display_name":"Mechanics of Materials"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9287999868392944,"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/conformational-isomerism","display_name":"Conformational isomerism","score":0.6377674341201782},{"id":"https://openalex.org/keywords/dual-mode","display_name":"Dual mode","score":0.6296660900115967},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.6292054057121277},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6289501190185547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5514296293258667},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5287337303161621},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2617954611778259},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.23125207424163818},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.12277966737747192},{"id":"https://openalex.org/keywords/molecule","display_name":"Molecule","score":0.11088153719902039},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0965488851070404},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.05597570538520813}],"concepts":[{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.6377674341201782},{"id":"https://openalex.org/C3019325349","wikidata":"https://www.wikidata.org/wiki/Q3874753","display_name":"Dual mode","level":2,"score":0.6296660900115967},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.6292054057121277},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6289501190185547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5514296293258667},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5287337303161621},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2617954611778259},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.23125207424163818},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.12277966737747192},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.11088153719902039},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0965488851070404},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.05597570538520813},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-733","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-733","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1989549063","https://openalex.org/W2407080277","https://openalex.org/W2750499125","https://openalex.org/W2936774411","https://openalex.org/W2963827914","https://openalex.org/W2972799770","https://openalex.org/W3016010032","https://openalex.org/W3092122846","https://openalex.org/W3095173472","https://openalex.org/W3095311338","https://openalex.org/W3095687747","https://openalex.org/W3096518646","https://openalex.org/W3097777922","https://openalex.org/W3125815078","https://openalex.org/W3160766462","https://openalex.org/W3161873870","https://openalex.org/W3162649911","https://openalex.org/W3162665866","https://openalex.org/W3163907627","https://openalex.org/W3189164341","https://openalex.org/W3200669029","https://openalex.org/W4287117254","https://openalex.org/W4287989347","https://openalex.org/W4288088457","https://openalex.org/W4292528629","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2023036309","https://openalex.org/W1972863456","https://openalex.org/W2392631856","https://openalex.org/W4379400065","https://openalex.org/W2355651228","https://openalex.org/W1992581387","https://openalex.org/W4254025658","https://openalex.org/W2768219827","https://openalex.org/W560347427","https://openalex.org/W2313428861"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,62,83,104],"present":[4],"an":[5,140],"in-depth":[6],"study":[7],"on":[8,131,164],"online":[9,19,36,50,58,96],"attention":[10,70,78,154,177],"mechanisms":[11],"and":[12,20,43,80,88,97,126,139,158,167],"distillation":[13,46],"techniques":[14],"for":[15],"dual-mode":[16,28,109,150,173],"(i.e.,":[17],"joint":[18],"offline)":[21],"ASR":[22],"using":[23,68,152,175],"the":[24,27,72,85,101,120,136,148,165,172],"Conformer":[25,29,73,110],"Transducer.In":[26],"Transducer":[30],"model,":[31],"layers":[32],"can":[33],"function":[34],"in":[35,54,71,100],"or":[37],"offline":[38,48,98],"mode":[39,51],"while":[40],"sharing":[41],"parameters,":[42],"in-place":[44],"knowledge":[45,102],"from":[47,67],"to":[49,56,76,171],"is":[52],"applied":[53],"training":[55],"improve":[57],"accuracy.In":[59],"our":[60],"study,":[61],"first":[63],"demonstrate":[64],"accuracy":[65],"improvements":[66],"chunked":[69,153],"encoder":[74],"compared":[75,170],"autoregressive":[77,176],"with":[79,92,178],"without":[81],"lookahead.Furthermore,":[82],"explore":[84],"efficient":[86],"KLD":[87,90],"1-best":[89],"losses":[91],"different":[93,134],"shifts":[94],"between":[95],"outputs":[99],"distillation.Finally,":[103],"show":[105,146],"that":[106,111,147],"a":[107],"simplified":[108],"only":[112],"has":[113],"mode-specific":[114,124],"self-attention":[115],"performs":[116],"equally":[117],"well":[118],"as":[119],"one":[121],"also":[122],"having":[123],"convolutions":[125],"normalization.Our":[127],"experiments":[128],"are":[129],"based":[130],"two":[132],"very":[133],"datasets:":[135],"Librispeech":[137,166],"task":[138],"internal":[141],"corpus":[142],"of":[143],"medical":[144,168],"conversations.Results":[145],"proposed":[149],"system":[151,174],"yields":[155],"5":[156],"%":[157,160],"4":[159],"relative":[161],"WER":[162],"improvement":[163],"tasks,":[169],"similar":[179],"average":[180],"lookahead.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
