{"id":"https://openalex.org/W3114420835","doi":"https://doi.org/10.1109/gcce50665.2020.9291906","title":"Integration of Accent Sandhi and Prosodic Features Estimation for Japanese Text-to-Speech Synthesis","display_name":"Integration of Accent Sandhi and Prosodic Features Estimation for Japanese Text-to-Speech Synthesis","publication_year":2020,"publication_date":"2020-10-13","ids":{"openalex":"https://openalex.org/W3114420835","doi":"https://doi.org/10.1109/gcce50665.2020.9291906","mag":"3114420835"},"language":"en","primary_location":{"id":"doi:10.1109/gcce50665.2020.9291906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce50665.2020.9291906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 9th 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/A5019687582","display_name":"Daisuke Fujimaki","orcid":null},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Fujimaki","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082389304","display_name":"Akinori Ito","orcid":"https://orcid.org/0000-0002-8835-7877"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinori Ito","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.17017173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"358","last_page":"359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9948999881744385,"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/T12031","display_name":"Speech and dialogue systems","score":0.9883999824523926,"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/stress","display_name":"Stress (linguistics)","score":0.8458766937255859},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8131097555160522},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6950525045394897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6805710196495056},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6793114542961121},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6734553575515747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.570035457611084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5471727252006531},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.45308130979537964},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.44213658571243286},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4219660460948944},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.41881853342056274},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.28841739892959595},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17398527264595032},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05897626280784607}],"concepts":[{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.8458766937255859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8131097555160522},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6950525045394897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6805710196495056},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6793114542961121},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6734553575515747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.570035457611084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5471727252006531},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.45308130979537964},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.44213658571243286},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4219660460948944},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.41881853342056274},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.28841739892959595},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17398527264595032},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05897626280784607},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce50665.2020.9291906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce50665.2020.9291906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 9th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6814346892","display_name":"Research and development of multi-modal interactive English learning system based on deep learning","funder_award_id":"17H00823","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2102003408","https://openalex.org/W2480794579","https://openalex.org/W2600818048","https://openalex.org/W2949676527","https://openalex.org/W2963945466","https://openalex.org/W4285719527","https://openalex.org/W6675380101","https://openalex.org/W6722151796"],"related_works":["https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W4298046075","https://openalex.org/W2334135487","https://openalex.org/W4207066001","https://openalex.org/W2381837697","https://openalex.org/W162378616","https://openalex.org/W4251666207","https://openalex.org/W2087397317","https://openalex.org/W2350046259"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"Japanese":[3,53],"text-to-speech":[4],"(TTS)":[5],"synthesis":[6],"methods":[7],"have":[8],"been":[9],"actively":[10],"researched.":[11],"We":[12],"need":[13],"to":[14,55],"estimate":[15],"appropriate":[16],"prosodic":[17,45,96],"information":[18],"for":[19,52],"generating":[20],"a":[21,75],"high-quality":[22],"synthetic":[23],"speech.":[24],"However,":[25],"manual":[26],"annotation":[27,32],"is":[28],"costly,":[29],"and":[30,44,78,91],"automatic":[31],"introduces":[33],"estimation":[34,47,98],"errors.":[35],"This":[36],"paper":[37],"examines":[38],"the":[39,49,57,66,71,83,92,95],"integration":[40],"of":[41,65,85,94],"accent":[42,87],"sandhi":[43],"feature":[46,97],"in":[48],"acoustic":[50],"modeling":[51],"TTS":[54],"overcome":[56],"problems.":[58],"The":[59],"proposed":[60],"method":[61],"achieves":[62],"total":[63],"optimization":[64],"F0":[67],"model":[68],"by":[69],"using":[70],"linguistic":[72],"features":[73],"from":[74],"dictionary.":[76],"Objective":[77],"subjective":[79],"evaluations":[80],"confirmed":[81],"that":[82],"cost":[84],"creating":[86],"labels":[88],"was":[89,99],"reduced,":[90],"accuracy":[93],"improved.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}