{"id":"https://openalex.org/W4416799984","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249392","title":"Phoneme-Grapheme Dictionary-Based Prompting for Robust Proper Noun Recognition in Japanese ASR","display_name":"Phoneme-Grapheme Dictionary-Based Prompting for Robust Proper Noun Recognition in Japanese ASR","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799984","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249392"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5120093696","display_name":"Ryuga Sugano","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuga Sugano","raw_affiliation_strings":["NHK Science and Technology Laboratories,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NHK Science and Technology Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025519045","display_name":"Hiroaki Sato","orcid":"https://orcid.org/0000-0002-2176-0215"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroaki Sato","raw_affiliation_strings":["NHK Science and Technology Laboratories,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NHK Science and Technology Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120093695","display_name":"Asahi Sakuma","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Asahi Sakuma","raw_affiliation_strings":["NHK Science and Technology Laboratories,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NHK Science and Technology Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006683103","display_name":"Tadashi Kumano","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tadashi Kumano","raw_affiliation_strings":["NHK Science and Technology Laboratories,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NHK Science and Technology Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103084561","display_name":"Yoshihiko Kawai","orcid":"https://orcid.org/0000-0002-0811-9095"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Kawai","raw_affiliation_strings":["NHK Science and Technology Laboratories,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NHK Science and Technology Laboratories,Tokyo,Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"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,Pittsburgh,PA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,PA,USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17666644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"968","last_page":"973"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.970300018787384,"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":0.970300018787384,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.007600000128149986,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.007199999876320362,"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/word-error-rate","display_name":"Word error rate","score":0.4864000082015991},{"id":"https://openalex.org/keywords/kanji","display_name":"Kanji","score":0.45879998803138733},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.4352000057697296},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41769999265670776},{"id":"https://openalex.org/keywords/proper-noun","display_name":"Proper noun","score":0.384799987077713},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.29829999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7822999954223633},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.697700023651123},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5626999735832214},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5439000129699707},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4864000082015991},{"id":"https://openalex.org/C83535845","wikidata":"https://www.wikidata.org/wiki/Q82772","display_name":"Kanji","level":3,"score":0.45879998803138733},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C41417386","wikidata":"https://www.wikidata.org/wiki/Q147276","display_name":"Proper noun","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249392","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2766219058","https://openalex.org/W2886319145","https://openalex.org/W2936774411","https://openalex.org/W2937402758","https://openalex.org/W2962780374","https://openalex.org/W2973172693","https://openalex.org/W3097777922","https://openalex.org/W3097794466","https://openalex.org/W4372348570","https://openalex.org/W4385245566","https://openalex.org/W4385822890","https://openalex.org/W4392903329","https://openalex.org/W4402111702","https://openalex.org/W4402112192","https://openalex.org/W4402671877","https://openalex.org/W4406461621","https://openalex.org/W4406461843"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"End-to-End":[1],"(E2E)":[2],"speech":[3,62,99],"recognition":[4,63],"models":[5,17],"still":[6],"struggle":[7],"with":[8,79,112,144],"low-frequency":[9],"words":[10],"such":[11],"as":[12,95],"proper":[13,70,135],"nouns.":[14],"Whereas":[15],"Whisper":[16],"utilize":[18],"prompt-based":[19],"contextual":[20],"biasing":[21,37],"for":[22,69],"improvement,":[23],"Japanese":[24,125],"presents":[25],"a":[26,60,67],"challenge":[27],"because":[28],"of":[29],"its":[30],"non-unique":[31],"grapheme-phoneme":[32],"correspondence,":[33],"which":[34,72,108],"limits":[35],"the":[36,86,93,103,113,134,145],"effectiveness.":[38],"Furthermore,":[39],"rare":[40],"kanji":[41],"and":[42,76],"special":[43,81,106],"symbols":[44],"often":[45],"lead":[46],"to":[47,141],"out-of-vocabulary":[48],"(OOV)":[49],"issues,":[50],"preventing":[51],"model":[52,87,104],"processing.":[53],"To":[54],"address":[55],"these":[56,101],"problems,":[57],"we":[58],"propose":[59],"novel":[61],"method":[64,84,131],"that":[65,129],"leverages":[66],"dictionary":[68,94,121],"nouns,":[71],"stores":[73],"their":[74],"graphemes":[75,116],"phonemes,":[77],"along":[78],"assigned":[80],"tokens.":[82],"Our":[83],"biases":[85],"by":[88,119],"providing":[89],"phoneme":[90],"sequences":[91],"from":[92,139],"prompts.":[96],"When":[97],"input":[98],"matches":[100],"sequences,":[102],"outputs":[105],"tokens,":[107],"are":[109],"then":[110],"replaced":[111],"corresponding":[114],"correct":[115],"during":[117],"post-processing":[118],"utilizing":[120],"entries.":[122],"Experiments":[123],"on":[124],"CSJ":[126],"datasets":[127],"demonstrate":[128],"our":[130],"drastically":[132],"reduces":[133],"noun":[136],"error":[137],"rate":[138],"24.5%":[140],"0.6%":[142],"compared":[143],"conventional":[146],"grapheme-based":[147],"prompting":[148],"method.":[149]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}