{"id":"https://openalex.org/W4285412695","doi":"https://doi.org/10.1109/jstsp.2022.3190672","title":"Investigation of Japanese PnG BERT Language Model in Text-to-Speech Synthesis for Pitch Accent Language","display_name":"Investigation of Japanese PnG BERT Language Model in Text-to-Speech Synthesis for Pitch Accent Language","publication_year":2022,"publication_date":"2022-07-13","ids":{"openalex":"https://openalex.org/W4285412695","doi":"https://doi.org/10.1109/jstsp.2022.3190672"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2022.3190672","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3190672","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09829304.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09829304.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068072475","display_name":"Yusuke Yasuda","orcid":"https://orcid.org/0000-0002-2130-747X"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Yasuda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya City, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2130-747X","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya City, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Nagoya City, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8146-1279","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya City, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":1.9682,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8810273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"16","issue":"6","first_page":"1319","last_page":"1328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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":0.9987999796867371,"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/computer-science","display_name":"Computer science","score":0.7359158396720886},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.672467827796936},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5805445909500122},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5205976963043213},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5034508109092712},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.47608938813209534},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4322904050350189},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3262982964515686},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.15614047646522522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7359158396720886},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.672467827796936},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5805445909500122},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5205976963043213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5034508109092712},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.47608938813209534},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4322904050350189},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3262982964515686},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.15614047646522522},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2022.3190672","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3190672","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09829304.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2212.08321","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.08321","pdf_url":"https://arxiv.org/pdf/2212.08321","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1109/jstsp.2022.3190672","is_oa":true,"landing_page_url":"https://doi.org/10.1109/jstsp.2022.3190672","pdf_url":"https://ieeexplore.ieee.org/ielx7/4200690/9923627/09829304.pdf","source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[{"id":"https://openalex.org/G1491700317","display_name":null,"funder_award_id":"JPNP20006","funder_id":"https://openalex.org/F4320321680","funder_display_name":"New Energy and Industrial Technology Development Organization"}],"funders":[{"id":"https://openalex.org/F4320321680","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285412695.pdf","grobid_xml":"https://content.openalex.org/works/W4285412695.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W30677081","https://openalex.org/W179875071","https://openalex.org/W1522301498","https://openalex.org/W1578102511","https://openalex.org/W1972978214","https://openalex.org/W2405684687","https://openalex.org/W2600818048","https://openalex.org/W2765486990","https://openalex.org/W2767052532","https://openalex.org/W2791489977","https://openalex.org/W2886769154","https://openalex.org/W2889028433","https://openalex.org/W2892140764","https://openalex.org/W2896457183","https://openalex.org/W2907916773","https://openalex.org/W2946417913","https://openalex.org/W2948947170","https://openalex.org/W2962780374","https://openalex.org/W2963609956","https://openalex.org/W2963945466","https://openalex.org/W2964002616","https://openalex.org/W2964034111","https://openalex.org/W2964243274","https://openalex.org/W2970352191","https://openalex.org/W2972610613","https://openalex.org/W2972831865","https://openalex.org/W2973043900","https://openalex.org/W2973217961","https://openalex.org/W2990883660","https://openalex.org/W3015338123","https://openalex.org/W3015680182","https://openalex.org/W3016137096","https://openalex.org/W3081488690","https://openalex.org/W3097800663","https://openalex.org/W3113217815","https://openalex.org/W3153839229","https://openalex.org/W3161732385","https://openalex.org/W3162948689","https://openalex.org/W3163339651","https://openalex.org/W3196027980","https://openalex.org/W3197324626","https://openalex.org/W6631190155","https://openalex.org/W6634201745","https://openalex.org/W6636510571","https://openalex.org/W6739901393","https://openalex.org/W6742080785","https://openalex.org/W6745289305","https://openalex.org/W6754925833","https://openalex.org/W6757699683","https://openalex.org/W6767988751"],"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/W2072461533","https://openalex.org/W162378616","https://openalex.org/W4251666207","https://openalex.org/W2087397317"],"abstract_inverted_index":{"End-to-end":[0],"text-to-speech":[1],"synthesis":[2],"(TTS)":[3],"can":[4],"generate":[5],"highly":[6],"natural":[7],"synthetic":[8],"speech":[9],"from":[10,89],"raw":[11],"text.":[12],"However,":[13],"rendering":[14,32],"the":[15,29,49,58,71,76,96,127],"correct":[16,33],"pitch":[17,34,80,109,139],"accents":[18],"is":[19],"still":[20],"a":[21,44,151],"challenging":[22],"problem":[23],"for":[24,54],"end-to-end":[25,38],"TTS.":[26,55,102],"To":[27],"tackle":[28],"challenge":[30],"of":[31,60,85,98,129],"accent":[35,110,148],"in":[36,48,150],"Japanese":[37,67],"TTS,":[39],"we":[40,105],"adopt":[41],"PnG":[42,64,86,107,130,142],"BERT,":[43],"self-supervised":[45],"pretrained":[46],"model":[47],"character":[50],"and":[51,141],"phoneme":[52],"domain":[53],"We":[56,82],"investigate":[57],"effects":[59],"features":[61,88,128],"captured":[62,132],"by":[63,69,94,112,133],"BERT":[65,87,108,131,143],"on":[66,147],"TTS":[68],"modifying":[70],"fine-tuning":[72,113],"condition":[73],"to":[74,92],"determine":[75],"conditions":[77],"helpful":[78,137],"inferring":[79,138],"accents.":[81],"manipulate":[83],"content":[84],"being":[90],"text-oriented":[91],"speech-oriented":[93],"changing":[95],"number":[97],"fine-tuned":[99],"layers":[100],"during":[101],"In":[103],"addition,":[104],"teach":[106],"information":[111,136],"with":[114],"tone":[115],"prediction":[116],"as":[117],"an":[118],"additional":[119],"downstream":[120],"task.":[121],"Our":[122],"experimental":[123],"results":[124],"show":[125],"that":[126],"pretraining":[134],"contain":[135],"accent,":[140],"outperforms":[144],"baseline":[145],"Tacotron":[146],"correctness":[149],"listening":[152],"test.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2022-07-14T00:00:00"}