{"id":"https://openalex.org/W4416799779","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249116","title":"Reducing Orthographic Dependency on Paired Data by Probabilistic Integration via Syllabogram for Japanese Dialogue Speech Recognition","display_name":"Reducing Orthographic Dependency on Paired Data by Probabilistic Integration via Syllabogram for Japanese Dialogue Speech Recognition","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799779","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249116"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249116","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/A5018403421","display_name":"Ryu Takeda","orcid":"https://orcid.org/0009-0007-0518-6245"},"institutions":[{"id":"https://openalex.org/I4210110027","display_name":"Sanken Electric (Japan)","ror":"https://ror.org/01v07hj96","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110027"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryu Takeda","raw_affiliation_strings":["SANKEN, The University of Osaka,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SANKEN, The University of Osaka,Japan","institution_ids":["https://openalex.org/I4210110027"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614400","display_name":"Kazunori Komatani","orcid":"https://orcid.org/0000-0002-6052-600X"},"institutions":[{"id":"https://openalex.org/I4210110027","display_name":"Sanken Electric (Japan)","ror":"https://ror.org/01v07hj96","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110027"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Komatani","raw_affiliation_strings":["SANKEN, The University of Osaka,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SANKEN, The University of Osaka,Japan","institution_ids":["https://openalex.org/I4210110027"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.17661917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"549","last_page":"554"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.4537999927997589,"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":0.4537999927997589,"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":0.42649999260902405,"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":0.02669999934732914,"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/robustness","display_name":"Robustness (evolution)","score":0.5450999736785889},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5449000000953674},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5353999733924866},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4781999886035919},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.44670000672340393},{"id":"https://openalex.org/keywords/orthographic-projection","display_name":"Orthographic projection","score":0.39980000257492065},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.391400009393692},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.38179999589920044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760000228881836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6826000213623047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6352999806404114},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5450999736785889},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5353999733924866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5088000297546387},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.44670000672340393},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249116","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249116","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":[{"id":"https://openalex.org/G4462423279","display_name":null,"funder_award_id":"JP23K28147,JP22H00536","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W198720948","https://openalex.org/W1976582129","https://openalex.org/W2052666245","https://openalex.org/W2107223151","https://openalex.org/W2109681258","https://openalex.org/W2597891111","https://openalex.org/W2766219058","https://openalex.org/W2883586237","https://openalex.org/W2888779557","https://openalex.org/W2889445100","https://openalex.org/W2962780374","https://openalex.org/W2963027641","https://openalex.org/W2972541922","https://openalex.org/W2972625221","https://openalex.org/W3151526698","https://openalex.org/W4297841733","https://openalex.org/W4385822995","https://openalex.org/W4385823316","https://openalex.org/W4385823436","https://openalex.org/W4388821450","https://openalex.org/W4389010491","https://openalex.org/W4392911130","https://openalex.org/W4402111987","https://openalex.org/W4402112104","https://openalex.org/W4402112288","https://openalex.org/W4402670040","https://openalex.org/W4402714986"],"related_works":[],"abstract_inverted_index":{"Character":[0],"end-to-end":[1],"ASR":[2,37],"(C-ASR)":[3],"models":[4,43,77,99],"fail":[5],"to":[6,116],"recognize":[7],"the":[8,25,45,48,75,82,101,134,149],"spelling":[9],"of":[10,35,47,74,81,151],"words":[11],"that":[12,64,130,148],"are":[13,50],"absent":[14],"from":[15,62,66,154],"paired":[16,26],"data":[17,27],"(audio":[18],"and":[19,39,78,97,141,156],"text).":[20],"This":[21],"orthographic":[22],"dependency":[23],"on":[24,95],"can":[28],"be":[29],"resolved":[30],"by":[31],"using":[32,112,124],"a":[33,71,88,108,113],"cascade":[34],"syllable":[36],"(S-ASR)":[38],"syllable-to-character":[40],"translation":[41],"(SCT)":[42],"once":[44],"pronunciations":[46],"text":[49],"given":[51],"as":[52],"syllabograms":[53],"in":[54],"model":[55,132],"training.":[56],"However,":[57],"this":[58],"method's":[59],"performance":[60],"suffers":[61],"errors":[63],"propagate":[65],"each":[67,161],"model.":[68,84,163],"We":[69,145],"propose":[70],"probabilistic":[72],"integration":[73,150],"two":[76],"robust":[79],"training":[80],"SCT":[83,98,159],"The":[85,105],"former":[86],"provides":[87],"global":[89],"score":[90],"for":[91],"better":[92],"estimations":[93],"based":[94],"S-ASR":[96,157],"during":[100],"blockwise":[102],"beam":[103],"search.":[104],"latter":[106],"introduces":[107],"pronunciation":[109],"error":[110],"generator":[111],"mask":[114],"token":[115],"increase":[117],"robustness":[118],"against":[119],"SASR":[120],"errors.":[121],"Experimental":[122],"results":[123,153],"real":[125],"Japanese":[126],"dialogue":[127],"corpora":[128],"showed":[129,147],"our":[131],"outperformed":[133,160],"naive":[135],"cascading":[136],"with":[137,158],"no":[138],"probability,":[139],"C-ASR,":[140],"other":[142],"open":[143],"models.":[144],"also":[146],"recognition":[152],"C-ASR":[155],"isolated":[162]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}