{"id":"https://openalex.org/W7126023789","doi":"https://doi.org/10.1109/icfsp67350.2025.11353632","title":"Pitch Accent Pattern Transcription in Tokyo and Osaka Japanese Using Whisper-Derived Features","display_name":"Pitch Accent Pattern Transcription in Tokyo and Osaka Japanese Using Whisper-Derived Features","publication_year":2025,"publication_date":"2025-09-10","ids":{"openalex":"https://openalex.org/W7126023789","doi":"https://doi.org/10.1109/icfsp67350.2025.11353632"},"language":null,"primary_location":{"id":"doi:10.1109/icfsp67350.2025.11353632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfsp67350.2025.11353632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Frontiers of Signal Processing (ICFSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5077272926","display_name":"Hiroto Noguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I42999171","display_name":"Sophia University","ror":"https://ror.org/01nckkm68","country_code":"JP","type":"education","lineage":["https://openalex.org/I42999171"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hiroto Noguchi","raw_affiliation_strings":["Institute of Education/Sophia University Institute of Science Tokyo/ Graduate School of Languages and Linguistics,Chiba/Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Education/Sophia University Institute of Science Tokyo/ Graduate School of Languages and Linguistics,Chiba/Tokyo,Japan","institution_ids":["https://openalex.org/I42999171"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5077272926"],"corresponding_institution_ids":["https://openalex.org/I42999171"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.65997785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"65","last_page":"68"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6543999910354614,"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":0.6543999910354614,"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":0.25110000371932983,"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/T10863","display_name":"Voice and Speech Disorders","score":0.01979999989271164,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5774999856948853},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5666000247001648},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5273000001907349},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.48010000586509705},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4754999876022339},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.41359999775886536},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41350001096725464}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050000190734863},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5848000049591064},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5774999856948853},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5666000247001648},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5273000001907349},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5260000228881836},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4223000109195709},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.41359999775886536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.33629998564720154},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.311599999666214},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2777853878","wikidata":"https://www.wikidata.org/wiki/Q743569","display_name":"Phonetic transcription","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icfsp67350.2025.11353632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfsp67350.2025.11353632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Frontiers of Signal Processing (ICFSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5616798996925354,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W189957710","https://openalex.org/W1502984613","https://openalex.org/W1514285833","https://openalex.org/W2011301426","https://openalex.org/W2115013739","https://openalex.org/W2191779130","https://openalex.org/W2492115799","https://openalex.org/W2492546578","https://openalex.org/W2979826702","https://openalex.org/W2997591727","https://openalex.org/W3035965352","https://openalex.org/W3150635270","https://openalex.org/W7084100420"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"an":[3,89],"automated":[4],"method":[5],"for":[6,57,64,80,86,132],"Japanese":[7],"pitch-accent":[8],"transcription":[9],"that":[10,117],"combines":[11],"Whisper-derived":[12],"hidden-state":[13],"embeddings":[14],"with":[15,88,108],"neural":[16,24],"network":[17,25],"classifiers.":[18],"Three":[19],"architectures\u2014multilayer":[20],"perceptron":[21],"(MLP),":[22],"convolutional":[23],"(CNN),":[26],"and":[27,38,44,82,104],"bidirectional":[28],"long":[29],"short-term":[30],"memory":[31],"(BiLSTM)\u2014are":[32],"evaluated":[33],"on":[34,128],"corpora":[35],"of":[36],"Tokyo":[37,76],"Osaka":[39,84],"dialects":[40],"under":[41],"identical":[42],"preprocessing":[43],"modeling":[45],"protocols.":[46],"In":[47],"within-dialect":[48],"experiments,":[49],"the":[50,53,60,95,109],"MLP":[51],"attains":[52],"best":[54,63,96],"mora-level":[55],"accuracy":[56],"Tokyo,":[58],"whereas":[59],"CNN":[61],"performs":[62],"Osaka.":[65],"A":[66],"cross-dialect":[67,118],"transfer":[68,119],"condition":[69],"is":[70],"also":[71],"tested":[72],"in":[73],"which":[74],"all":[75,83],"data":[77,85],"are":[78],"used":[79],"training":[81],"evaluation":[87],"unchanged":[90],"pipeline.":[91],"Under":[92],"this":[93],"setting,":[94],"configuration":[97],"reaches":[98],"69.13%":[99],"mora":[100],"accuracy,":[101,107],"0.678":[102],"macro-F1,":[103],"22.82%":[105],"word-level":[106],"other":[110],"configurations":[111],"slightly":[112],"lower.":[113],"These":[114],"findings":[115],"indicate":[116],"remains":[120],"challenging":[121],"without":[122],"explicit":[123],"adaptation,":[124],"motivating":[125],"future":[126],"work":[127],"simple,":[129],"reproducible":[130],"strategies":[131],"target-dialect":[133],"robustness.":[134]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-30T00:00:00"}