{"id":"https://openalex.org/W4406461621","doi":"https://doi.org/10.1109/slt61566.2024.10832281","title":"Contextualized Automatic Speech Recognition With Dynamic Vocabulary","display_name":"Contextualized Automatic Speech Recognition With Dynamic Vocabulary","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461621","doi":"https://doi.org/10.1109/slt61566.2024.10832281"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","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/A5091425252","display_name":"Yui Sudo","orcid":"https://orcid.org/0000-0003-2094-6701"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yui Sudo","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd.,,Japan"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd.,,Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108536736","display_name":"Y. Fukumoto","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yosuke Fukumoto","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd.,,Japan"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd.,,Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100601048","display_name":"Muhammad Shakeel","orcid":"https://orcid.org/0000-0003-2210-7039"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Muhammad Shakeel","raw_affiliation_strings":["Honda Research Institute Japan Co., Ltd.,,Japan"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan Co., Ltd.,,Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033862822","display_name":"Yifan Peng","orcid":"https://orcid.org/0000-0002-8581-8674"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Peng","raw_affiliation_strings":["Carnegie Mellon University,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091425252"],"corresponding_institution_ids":["https://openalex.org/I1283473643"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.70879773,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"78","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T12031","display_name":"Speech and dialogue systems","score":0.9958000183105469,"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/computer-science","display_name":"Computer science","score":0.7864365577697754},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7088963389396667},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.681025505065918},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5450248718261719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.419497013092041},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2951164245605469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864365577697754},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7088963389396667},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.681025505065918},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5450248718261719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.419497013092041},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2951164245605469},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832281","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1965255698","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2627092829","https://openalex.org/W2766219058","https://openalex.org/W2886319145","https://openalex.org/W2888779557","https://openalex.org/W2889012072","https://openalex.org/W2937402758","https://openalex.org/W2962780374","https://openalex.org/W2963240019","https://openalex.org/W2973172693","https://openalex.org/W3007433671","https://openalex.org/W3011339933","https://openalex.org/W3097239815","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W3198004110","https://openalex.org/W3211278025","https://openalex.org/W4221165942","https://openalex.org/W4225289150","https://openalex.org/W4226292626","https://openalex.org/W4372260554","https://openalex.org/W4372267461","https://openalex.org/W4385822246","https://openalex.org/W4385822271","https://openalex.org/W4385823173","https://openalex.org/W4385823261","https://openalex.org/W4385823316","https://openalex.org/W4388017359","https://openalex.org/W4391021675","https://openalex.org/W4391021762","https://openalex.org/W4392903019","https://openalex.org/W4392903329","https://openalex.org/W4399447692","https://openalex.org/W4402111365","https://openalex.org/W4402112192","https://openalex.org/W4402671610","https://openalex.org/W4402671877","https://openalex.org/W6623517193","https://openalex.org/W6638749077","https://openalex.org/W6675365184","https://openalex.org/W6779469704","https://openalex.org/W6847363464","https://openalex.org/W6869410597"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Deep":[0],"biasing":[1],"(DB)":[2],"enhances":[3],"the":[4,60,66,79,83,122,129,144,157,161,175],"performance":[5],"of":[6,32,115],"end-to-end":[7],"automatic":[8],"speech":[9],"recognition":[10],"(E2E-ASR)":[11],"models":[12],"for":[13],"rare":[14],"words":[15],"or":[16,72],"contextual":[17],"phrases":[18,29],"using":[19],"a":[20,35,89,103,109,113],"bias":[21,28,93,104,130,162],"list.":[22],"However,":[23,74],"most":[24],"existing":[25,116],"methods":[26],"treat":[27],"as":[30,108],"sequences":[31],"subwords":[33],"in":[34,77,102,149],"predefined":[36],"static":[37],"vocabulary.":[38],"This":[39,86,119,132],"naive":[40],"sequence":[41,114],"decomposition":[42],"produces":[43],"unnatural":[44],"token":[45],"patterns,":[46],"significantly":[47],"lowering":[48],"their":[49],"occurrence":[50],"probability.":[51],"More":[52],"advanced":[53],"techniques":[54],"address":[55],"this":[56],"problem":[57],"by":[58,170],"expanding":[59],"vocabulary":[61,91],"with":[62,174],"additional":[63,84],"modules,":[64],"including":[65],"external":[67],"language":[68],"model":[69],"shallow":[70],"fusion":[71],"rescoring.":[73],"they":[75],"result":[76],"increasing":[78],"workload":[80],"due":[81],"to":[82,124,137],"modules.":[85],"paper":[87],"proposes":[88],"dynamic":[90],"where":[92],"tokens":[94],"can":[95],"be":[96],"added":[97],"during":[98],"inference.":[99],"Each":[100],"entry":[101],"list":[105],"is":[106,134],"represented":[107],"single":[110],"token,":[111],"unlike":[112],"subword":[117,126],"tokens.":[118],"approach":[120],"eliminates":[121],"need":[123],"learn":[125],"dependencies":[127],"within":[128],"phrases.":[131],"method":[133,159],"easily":[135],"applied":[136],"various":[138],"architectures":[139],"because":[140],"it":[141],"only":[142],"expands":[143],"embedding":[145],"and":[146,167],"output":[147],"layers":[148],"common":[150],"E2E-ASR":[151],"architectures.":[152],"Experimental":[153],"results":[154],"demonstrate":[155],"that":[156],"proposed":[158],"improves":[160],"phrase":[163],"WER":[164],"on":[165],"English":[166],"Japanese":[168],"datasets":[169],"$3.1-4.9$":[171],"points":[172],"compared":[173],"conventional":[176],"DB":[177],"method.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}