{"id":"https://openalex.org/W7148385867","doi":"https://doi.org/10.1109/asru65441.2025.11434772","title":"PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation","display_name":"PARCO: Phoneme-Augmented Robust Contextual ASR via Contrastive Entity Disambiguation","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148385867","doi":"https://doi.org/10.1109/asru65441.2025.11434772"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132801574","display_name":"Jiajun He","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jiajun He","raw_affiliation_strings":["Nagoya University,Graduate School of Informatics,Nagoya,Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Graduate School of Informatics,Nagoya,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016242318","display_name":"Naoki Sawada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoki Sawada","raw_affiliation_strings":["AI Lab CyberAgent,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"AI Lab CyberAgent,Tokyo,Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108952065","display_name":"Koichi Miyazaki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichi Miyazaki","raw_affiliation_strings":["AI Lab CyberAgent,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"AI Lab CyberAgent,Tokyo,Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132801075","display_name":"Tomoki Toda","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Information Technology Center,Nagoya,Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Information Technology Center,Nagoya,Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5132801574"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":2.1819,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9293656,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7997000217437744,"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":0.7997000217437744,"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/T10028","display_name":"Topic Modeling","score":0.0284000001847744,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.02759999968111515,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.35089999437332153},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.29600000381469727},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.28519999980926514},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.24889999628067017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6233000159263611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5058000087738037},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44690001010894775},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2815999984741211},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.24889999628067017},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.23409999907016754}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44036662578582764,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2526425061","https://openalex.org/W2886319145","https://openalex.org/W2889012072","https://openalex.org/W2937402758","https://openalex.org/W2963242190","https://openalex.org/W2973172693","https://openalex.org/W3095918555","https://openalex.org/W3096318498","https://openalex.org/W3097777922","https://openalex.org/W3140235797","https://openalex.org/W3160413945","https://openalex.org/W3202419788","https://openalex.org/W4221139374","https://openalex.org/W4225289150","https://openalex.org/W4225985539","https://openalex.org/W4226292626","https://openalex.org/W4283832239","https://openalex.org/W4297841426","https://openalex.org/W4319862232","https://openalex.org/W4372348570","https://openalex.org/W4387698265","https://openalex.org/W4391021742","https://openalex.org/W4392487628","https://openalex.org/W4392903019","https://openalex.org/W4392903078","https://openalex.org/W4392903240","https://openalex.org/W4392903329","https://openalex.org/W4392904444","https://openalex.org/W4402111736","https://openalex.org/W4402111987","https://openalex.org/W4402112425","https://openalex.org/W4402115917","https://openalex.org/W4402671877","https://openalex.org/W4406461641","https://openalex.org/W4406461849","https://openalex.org/W4406858740","https://openalex.org/W4406859274","https://openalex.org/W4406859923","https://openalex.org/W4408345773","https://openalex.org/W4408354612","https://openalex.org/W4411086746","https://openalex.org/W4415432605"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"speech":[1],"recognition":[2,15],"(ASR)":[3],"systems":[4],"struggle":[5],"with":[6],"domain-specific":[7],"named":[8],"entities,":[9],"especially":[10],"homophones.":[11],"Contextual":[12,50],"ASR":[13,51],"improves":[14],"but":[16],"often":[17],"fails":[18],"to":[19,25,38],"capture":[20],"fine-grained":[21],"phoneme":[22],"variations":[23],"due":[24],"limited":[26],"entity":[27,54,62,68,77],"diversity.":[28],"Moreover,":[29],"prior":[30],"methods":[31],"treat":[32],"entities":[33],"as":[34],"independent":[35],"tokens,":[36],"leading":[37],"incomplete":[39],"multi-token":[40],"biasing.":[41],"To":[42],"address":[43],"these":[44],"issues,":[45],"we":[46],"propose":[47],"Phoneme-Augmented":[48],"Robust":[49],"via":[52],"COntrastive":[53],"disambiguation":[55],"(PARCO),":[56],"which":[57],"integrates":[58],"phoneme-aware":[59],"encoding,":[60],"contrastive":[61],"disambiguation,":[63],"entity-level":[64],"supervision,":[65],"and":[66,79,97,124],"hierarchical":[67],"filtering.":[69],"These":[70],"components":[71],"enhance":[72],"phonetic":[73],"discrimination,":[74],"ensure":[75],"complete":[76],"retrieval,":[78],"reduce":[80],"false":[81],"positives":[82],"under":[83,108],"uncertainty.":[84],"Experiments":[85],"show":[86],"that":[87],"PARCO":[88,114],"achieves":[89],"CER":[90],"of":[91,99],"$4.22":[92],"\\%$":[93],"on":[94,105,119],"Chinese":[95],"AISHELL-1":[96],"WER":[98],"$\\mathbf{1":[100],"1.":[101],"1":[102],"4":[103],"\\%}$":[104],"English":[106],"DATA2":[107],"1,000":[109],"distractors,":[110],"significantly":[111],"outperforming":[112],"baselines.":[113],"also":[115],"demonstrates":[116],"robust":[117],"gains":[118],"out-of-domain":[120],"datasets":[121],"like":[122],"THCHS-30":[123],"LibriSpeech.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2026-04-03T00:00:00"}