{"id":"https://openalex.org/W3197654132","doi":"https://doi.org/10.21437/interspeech.2021-1693","title":"Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition","display_name":"Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197654132","doi":"https://doi.org/10.21437/interspeech.2021-1693","mag":"3197654132"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1693","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_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":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2107.01269","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071286568","display_name":"Niko Moritz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niko Moritz","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.884,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.838294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":86,"max":87},"biblio":{"volume":null,"issue":null,"first_page":"1822","last_page":"1826"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9973,"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":0.9915,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.6689512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6952281},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6689512},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.63349795},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.59767574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31212097},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","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":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1693","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_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":"http://arxiv.org/abs/2107.01269","pdf_url":"http://arxiv.org/pdf/2107.01269","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":"http://arxiv.org/abs/2107.01269","pdf_url":"http://arxiv.org/pdf/2107.01269","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":0,"referenced_works":[],"related_works":["https://openalex.org/W3196421258","https://openalex.org/W3179968364","https://openalex.org/W2938107654","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2382290278","https://openalex.org/W2376932109","https://openalex.org/W2358668433","https://openalex.org/W2151749779"],"abstract_inverted_index":{"Attention-based":[0],"end-to-end":[1,119],"automatic":[2],"speech":[3],"recognition":[4],"(ASR)":[5],"systems":[6,121],"have":[7],"recently":[8],"demonstrated":[9],"state-of-the-art":[10,123],"results":[11,100,124],"for":[12,26],"numerous":[13],"tasks.":[14,132],"However,":[15],"the":[16,45,58,64,107,116,126],"application":[17],"of":[18,66,109],"self-attention":[19,48,56,83,96],"and":[20,81,87,97,129],"attention-based":[21],"encoder-decoder":[22],"models":[23],"remains":[24],"challenging":[25],"streaming":[27,85,118],"ASR,":[28],"where":[29],"each":[30],"word":[31],"must":[32],"be":[33],"recognized":[34],"shortly":[35],"after":[36],"it":[37],"was":[38],"spoken.":[39],"In":[40],"this":[41],"work,":[42],"we":[43],"present":[44],"dual":[46],"causal/non-causal":[47],"(DCN)":[49],"architecture,":[50],"which":[51],"in":[52,72],"contrast":[53],"to":[54,61,79,102],"restricted":[55,82,95],"prevents":[57],"overall":[59],"context":[60],"grow":[62],"beyond":[63],"look-ahead":[65],"a":[67,73],"single":[68],"layer":[69],"when":[70],"used":[71],"deep":[74],"architecture.":[75],"DCN":[76],"is":[77],"compared":[78,101],"chunk-based":[80,103],"using":[84],"transformer":[86],"conformer":[88],"architectures,":[89],"showing":[90],"improved":[91],"ASR":[92,99,120,131],"performance":[93],"over":[94],"competitive":[98],"self-attention,":[104],"while":[105],"providing":[106],"advantage":[108],"frame-synchronous":[110],"processing.":[111],"Combined":[112],"with":[113],"triggered":[114],"attention,":[115],"proposed":[117],"obtained":[122],"on":[125],"LibriSpeech,":[127],"HKUST,":[128],"Switchboard":[130]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3197654132","counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-04-18T12:20:50.544597","created_date":"2021-09-13"}