{"id":"https://openalex.org/W4415433656","doi":"https://doi.org/10.21437/interspeech.2025-129","title":"DYNAC: Dynamic Vocabulary-based Non-Autoregressive Contextualization for Speech Recognition","display_name":"DYNAC: Dynamic Vocabulary-based Non-Autoregressive Contextualization for Speech Recognition","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433656","doi":"https://doi.org/10.21437/interspeech.2025-129"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-129","doi":"https://doi.org/10.21437/interspeech.2025-129","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-129","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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 2025","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.00422","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091425252","display_name":"Yui Sudo","orcid":"https://orcid.org/0000-0003-2094-6701","observed_orcids":["https://orcid.org/0000-0003-2094-6701"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yui Sudo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yosuke Fukumoto","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yosuke Fukumoto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100568412","display_name":"Muhammad Shakeel","orcid":"https://orcid.org/0000-0003-3822-0917","observed_orcids":["https://orcid.org/0000-0003-3822-0917"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Muhammad Shakeel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0001-7875-2964","observed_orcids":["https://orcid.org/0000-0001-7875-2964"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069664539","display_name":"Chyi-Jiunn Lin","orcid":"https://orcid.org/0000-0002-2447-9330","observed_orcids":["https://orcid.org/0000-0002-2447-9330"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chyi-Jiunn Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631","observed_orcids":["https://orcid.org/0000-0002-5970-8631"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.07,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79637144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2215","last_page":"2219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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 and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.0,"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/T10028","display_name":"Topic Modeling","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dynamic-vocabulary","display_name":"dynamic vocabulary","score":0.9049999713897705},{"id":"https://openalex.org/keywords/contextual-biasing","display_name":"contextual biasing","score":0.8949999809265137},{"id":"https://openalex.org/keywords/non-autoregressive-models","display_name":"non-autoregressive models","score":0.8339999914169312},{"id":"https://openalex.org/keywords/connectionist-temporal-classification","display_name":"connectionist temporal classification","score":0.9739999771118164},{"id":"https://openalex.org/keywords/conditional-independence-assumption","display_name":"conditional independence assumption","score":0.6029999852180481},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.4749999940395355}],"concepts":[{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.6259999871253967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5429999828338623},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5238999724388123},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3750999867916107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34450000524520874},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3133000135421753},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30979999899864197},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2854999899864197},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C137584468","wikidata":"https://www.wikidata.org/wiki/Q35395","display_name":"Phonetics","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2025-129","doi":"https://doi.org/10.21437/interspeech.2025-129","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-129","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.00422","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.00422","pdf_url":"https://arxiv.org/pdf/2506.00422","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.00422","doi":"https://doi.org/10.48550/arxiv.2506.00422","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.00422","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.00422","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.00422","pdf_url":"https://arxiv.org/pdf/2506.00422","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415433656.pdf","grobid_xml":"https://content.openalex.org/works/W4415433656.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4402671877"],"related_works":["https://openalex.org/W4406461621","https://openalex.org/W4415433101","https://openalex.org/W4402112174","https://openalex.org/W7155076999","https://openalex.org/W4306887117","https://openalex.org/W3198004110","https://openalex.org/W275014237","https://openalex.org/W201960594","https://openalex.org/W3096147599","https://openalex.org/W2952886436"],"abstract_inverted_index":{"Contextual":[0],"biasing":[1],"(CB)":[2],"improves":[3,31],"automatic":[4],"speech":[5],"recognition":[6],"for":[7],"rare":[8],"and":[9,65,99],"unseen":[10],"phrases.":[11],"Recent":[12],"studies":[13],"have":[14],"introduced":[15],"dynamic":[16,40,66,82,91,100],"vocabulary,":[17,92],"which":[18],"represents":[19],"context":[20],"phrases":[21],"as":[22,50],"expandable":[23],"tokens":[24,101],"in":[25,121],"autoregressive":[26],"(AR)":[27],"models.":[28],"This":[29,68],"method":[30,79],"CB":[32],"accuracy":[33],"but":[34],"with":[35,117],"slow":[36],"inference":[37],"speed.":[38],"While":[39],"vocabulary":[41,83],"can":[42],"be":[43],"applied":[44],"to":[45,60],"non-autoregressive":[46],"(NAR)":[47],"models,":[48],"such":[49],"connectionist":[51],"temporal":[52],"classification":[53],"(CTC),":[54],"the":[55,88,104,126],"conditional":[56],"independence":[57],"assumption":[58],"fails":[59],"capture":[61],"dependencies":[62,96],"between":[63,97],"static":[64,98],"tokens.":[67],"paper":[69],"proposes":[70],"DYNAC":[71,93,112],"(Dynamic":[72],"Vocabulary-based":[73],"NAR":[74],"Contextualization),":[75],"a":[76,118],"self-conditioned":[77],"CTC":[78],"that":[80,111],"integrates":[81],"into":[84],"intermediate":[85],"layers.":[86],"Conditioning":[87],"encoder":[89],"on":[90,125],"effectively":[94],"captures":[95],"while":[102],"reducing":[103],"real-time":[105],"factor":[106],"(RTF).":[107],"Experimental":[108],"results":[109],"show":[110],"reduces":[113],"RTF":[114],"by":[115],"81%":[116],"0.1-point":[119],"degradation":[120],"word":[122],"error":[123],"rate":[124],"LibriSpeech":[127],"960":[128],"test-clean":[129],"set.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-24T00:00:00"}