{"id":"https://openalex.org/W4388720314","doi":"https://doi.org/10.1109/gcce59613.2023.10315342","title":"Estimation Of Japanese Word Intelligibility Using CTC-based Phoneme Recognition","display_name":"Estimation Of Japanese Word Intelligibility Using CTC-based Phoneme Recognition","publication_year":2023,"publication_date":"2023-10-10","ids":{"openalex":"https://openalex.org/W4388720314","doi":"https://doi.org/10.1109/gcce59613.2023.10315342"},"language":"en","primary_location":{"id":"doi:10.1109/gcce59613.2023.10315342","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/gcce59613.2023.10315342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 12th Global Conference on Consumer Electronics (GCCE)","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/A5005545514","display_name":"Masaki Hattori","orcid":"https://orcid.org/0000-0002-9603-2132"},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaki Hattori","raw_affiliation_strings":["Yamagata University,Graduate School of Science and Engineering,Yamagata,Japan","Graduate School of Science and Engineering, Yamagata University, Yamagata, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yamagata University,Graduate School of Science and Engineering,Yamagata,Japan","institution_ids":["https://openalex.org/I112524849"]},{"raw_affiliation_string":"Graduate School of Science and Engineering, Yamagata University, Yamagata, Japan","institution_ids":["https://openalex.org/I112524849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054505593","display_name":"Kazuhiro Kondo","orcid":"https://orcid.org/0000-0003-2160-8683"},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Kondo","raw_affiliation_strings":["Yamagata University,Graduate School of Science and Engineering,Yamagata,Japan","Graduate School of Science and Engineering, Yamagata University, Yamagata, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yamagata University,Graduate School of Science and Engineering,Yamagata,Japan","institution_ids":["https://openalex.org/I112524849"]},{"raw_affiliation_string":"Graduate School of Science and Engineering, Yamagata University, Yamagata, Japan","institution_ids":["https://openalex.org/I112524849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I112524849"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16834812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"376","last_page":"377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9857000112533569,"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":0.974399983882904,"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/speech-recognition","display_name":"Speech recognition","score":0.7822831273078918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777596116065979},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6996263265609741},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6473345756530762},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6341524124145508},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.5649755001068115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.559090256690979},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.49901771545410156},{"id":"https://openalex.org/keywords/rhyme","display_name":"Rhyme","score":0.48188120126724243},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.363740473985672},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35861557722091675},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07270494103431702}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7822831273078918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777596116065979},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6996263265609741},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6473345756530762},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6341524124145508},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.5649755001068115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.559090256690979},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.49901771545410156},{"id":"https://openalex.org/C2777231075","wikidata":"https://www.wikidata.org/wiki/Q178715","display_name":"Rhyme","level":3,"score":0.48188120126724243},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.363740473985672},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35861557722091675},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07270494103431702},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce59613.2023.10315342","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/gcce59613.2023.10315342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 12th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"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":3,"referenced_works":["https://openalex.org/W2088337215","https://openalex.org/W3034729383","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W2382985347","https://openalex.org/W2370884321","https://openalex.org/W2392578242","https://openalex.org/W2352383092","https://openalex.org/W2368826553","https://openalex.org/W2038899728","https://openalex.org/W1980930823","https://openalex.org/W1969511479","https://openalex.org/W2148167314","https://openalex.org/W4389241220"],"abstract_inverted_index":{"The":[0,20],"purpose":[1],"of":[2,28,49,124],"this":[3,147],"study":[4],"is":[5,26,117,134],"to":[6,33,43,57,67,77,136],"estimate":[7,44],"subjective":[8,30,60],"Japanese":[9,21,35],"word":[10,36,144],"intelligibility":[11,45],"using":[12,155],"Connectionist":[13],"Temporal":[14],"Classification":[15],"(CTC)":[16],"based":[17],"phoneme":[18,152],"recognition.":[19],"Diagnostic":[22],"Rhyme":[23],"Test":[24],"(JDRT)":[25],"one":[27],"the":[29,47,79,96,99,103,121,125,159],"evaluation":[31],"methods":[32],"measure":[34],"intelligibility.":[37,145],"We":[38],"propose":[39],"an":[40,55],"objective":[41],"method":[42,141],"from":[46],"output":[48,126],"automatic":[50],"speech":[51],"recognition":[52,153],"(ASR)":[53],"in":[54,75,84,102,107],"attempt":[56],"predict":[58],"its":[59],"value.":[61],"In":[62,146],"previous":[63],"studies,":[64],"we":[65,149],"attempted":[66],"use":[68,78],"hybrid":[69],"ASR":[70,74],"and":[71,157],"APIs":[72],"for":[73,142],"order":[76],"well-trained":[80],"acoustic":[81],"models":[82],"used":[83],"these":[85,89],"systems.":[86],"However,":[87],"since":[88],"systems":[90],"were":[91],"targeting":[92,120],"large":[93],"vocabulary":[94,101],"recognition,":[95],"mismatch":[97],"with":[98],"limited":[100],"JDRT":[104],"task":[105],"resulted":[106],"non-trivial":[108],"errors,":[109],"such":[110],"as":[111],"blank":[112],"token":[113],"output.":[114],"CTC,":[115],"which":[116],"trained":[118],"by":[119],"correct":[122],"answer":[123],"text":[127],"series":[128],"rather":[129],"than":[130],"frame-by-frame,":[131],"like":[132],"HMM,":[133],"considered":[135],"be":[137],"a":[138,151],"more":[139],"suitable":[140],"estimating":[143],"paper,":[148],"constructed":[150],"model":[154],"CTC":[156],"simulated":[158],"JDRT.":[160]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}