{"id":"https://openalex.org/W4224932891","doi":"https://doi.org/10.1109/icassp43922.2022.9746212","title":"Polyphone Disambiguation and Accent Prediction Using Pre-Trained Language Models in Japanese TTS Front-End","display_name":"Polyphone Disambiguation and Accent Prediction Using Pre-Trained Language Models in Japanese TTS Front-End","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224932891","doi":"https://doi.org/10.1109/icassp43922.2022.9746212"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746212","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5034109894","display_name":"Rem Hida","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rem Hida","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086602359","display_name":"Masaki Hamada","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masaki Hamada","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056244588","display_name":"Chie Kamada","orcid":"https://orcid.org/0000-0001-6980-4494"},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chie Kamada","raw_affiliation_strings":["Sony Corporation of America,San Jose,CA,USA","Sony Corporation of America, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Sony Corporation of America,San Jose,CA,USA","institution_ids":["https://openalex.org/I2800278093"]},{"raw_affiliation_string":"Sony Corporation of America, San Jose, CA, USA","institution_ids":["https://openalex.org/I2800278093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011937407","display_name":"Emiru Tsunoo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emiru Tsunoo","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011704777","display_name":"Toshiyuki Sekiya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toshiyuki Sekiya","raw_affiliation_strings":["Sony Group Corporation,Tokyo,Japan","Sony Group Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Sony Group Corporation,Tokyo,Japan","institution_ids":[]},{"raw_affiliation_string":"Sony Group Corporation, Tokyo, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084435555","display_name":"Toshiyuki Kumakura","orcid":null},"institutions":[{"id":"https://openalex.org/I2800278093","display_name":"Sony Corporation (United States)","ror":"https://ror.org/05k91zb11","country_code":"US","type":"company","lineage":["https://openalex.org/I2800278093"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Toshiyuki Kumakura","raw_affiliation_strings":["Sony Corporation of America,San Jose,CA,USA","Sony Corporation of America, San Jose, CA, USA"],"affiliations":[{"raw_affiliation_string":"Sony Corporation of America,San Jose,CA,USA","institution_ids":["https://openalex.org/I2800278093"]},{"raw_affiliation_string":"Sony Corporation of America, San Jose, CA, USA","institution_ids":["https://openalex.org/I2800278093"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5034109894"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6233,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65923292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7132","last_page":"7136"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9969000220298767,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9951000213623047,"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/naturalness","display_name":"Naturalness","score":0.8605838418006897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7979077100753784},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.687926709651947},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6706464290618896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6442517638206482},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5643653273582458},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5596179366111755},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5417947769165039},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5015871524810791},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.43571603298187256},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4136055111885071},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.136726975440979},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08774974942207336}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8605838418006897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979077100753784},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.687926709651947},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6706464290618896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6442517638206482},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5643653273582458},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5596179366111755},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5417947769165039},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5015871524810791},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.43571603298187256},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4136055111885071},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.136726975440979},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08774974942207336},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746212","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W89093025","https://openalex.org/W100723821","https://openalex.org/W1940872118","https://openalex.org/W2064675550","https://openalex.org/W2147880316","https://openalex.org/W2600818048","https://openalex.org/W2765486990","https://openalex.org/W2794490148","https://openalex.org/W2880875857","https://openalex.org/W2896457183","https://openalex.org/W2964243274","https://openalex.org/W2972457126","https://openalex.org/W2972831865","https://openalex.org/W2972881244","https://openalex.org/W2973190645","https://openalex.org/W2973217961","https://openalex.org/W2974273066","https://openalex.org/W3007419862","https://openalex.org/W3015338123","https://openalex.org/W3033411150","https://openalex.org/W3034729383","https://openalex.org/W3081488690","https://openalex.org/W3095762785","https://openalex.org/W3128170746","https://openalex.org/W3161113899","https://openalex.org/W3163738228","https://openalex.org/W3171055158","https://openalex.org/W3196843885","https://openalex.org/W3196875702","https://openalex.org/W3197324626","https://openalex.org/W3197632081","https://openalex.org/W4385245566","https://openalex.org/W6603576222","https://openalex.org/W6604148822","https://openalex.org/W6640362995","https://openalex.org/W6682082992","https://openalex.org/W6739901393","https://openalex.org/W6745289305","https://openalex.org/W6750489868","https://openalex.org/W6752788575","https://openalex.org/W6755207826","https://openalex.org/W6765540686","https://openalex.org/W6767913650","https://openalex.org/W6778823374","https://openalex.org/W6779469704"],"related_works":["https://openalex.org/W117063597","https://openalex.org/W4289544804","https://openalex.org/W3031252497","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473"],"abstract_inverted_index":{"Although":[0],"end-to-end":[1],"text-to-speech":[2],"(TTS)":[3],"models":[4,61],"can":[5],"generate":[6],"natural":[7],"speech,":[8],"challenges":[9],"still":[10],"remain":[11],"when":[12],"it":[13],"comes":[14],"to":[15,75,127],"estimating":[16],"sentence-level":[17],"phonetic":[18],"and":[19,40,54,66,72,98,135],"prosodic":[20],"information":[21],"from":[22,51,58],"raw":[23],"text":[24],"in":[25,96,101,137],"Japanese":[26],"TTS":[27,112],"systems.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32],"propose":[33],"a":[34,111,119,122],"method":[35,46,89],"for":[36],"polyphone":[37],"disambiguation":[38],"(PD)":[39],"accent":[41,136],"prediction":[42],"(AP).":[43],"The":[44],"proposed":[45,88,116],"incorporates":[47],"explicit":[48,79],"features":[49,56,71],"extracted":[50,57],"morphological":[52],"analysis":[53],"implicit":[55,70],"pre-trained":[59],"language":[60],"(PLMs).":[62],"We":[63],"use":[64],"BERT":[65],"Flair":[67],"embeddings":[68],"as":[69,118],"examine":[73],"how":[74],"combine":[76],"them":[77],"with":[78,132],"features.":[80],"Our":[81],"objective":[82],"evaluation":[83],"results":[84,108],"showed":[85],"that":[86,110,128],"the":[87,91,104],"improved":[90],"accuracy":[92],"by":[93],"5.7":[94],"points":[95,100],"PD":[97],"6.0":[99],"AP.":[102],"Moreover,":[103],"perceptual":[105],"listening":[106],"test":[107],"confirmed":[109],"system":[113],"employing":[114],"our":[115],"model":[117],"front-end":[120],"achieved":[121],"mean":[123],"opinion":[124],"score":[125],"close":[126],"of":[129,139],"synthesized":[130],"speech":[131],"ground-truth":[133],"pronunciation":[134],"terms":[138],"naturalness.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}