{"id":"https://openalex.org/W2126028788","doi":"https://doi.org/10.1109/icassp.2011.5947406","title":"Tonal context labeling using quantized F0 symbols for improving tone correctness in average-voice-based speech synthesis","display_name":"Tonal context labeling using quantized F0 symbols for improving tone correctness in average-voice-based speech synthesis","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2126028788","doi":"https://doi.org/10.1109/icassp.2011.5947406","mag":"2126028788"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5002206098","display_name":"Vataya Chunwijitra","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Vataya Chunwijitra","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"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/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022405100","display_name":"Takao Kobayashi","orcid":"https://orcid.org/0000-0003-0387-8030"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takao Kobayashi","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.8628,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.80812064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4708","last_page":"4711"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9927999973297119,"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/correctness","display_name":"Correctness","score":0.851714015007019},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.811970591545105},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7765573859214783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7459176182746887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7366752028465271},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.7006566524505615},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5964145660400391},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.572716474533081},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13686245679855347},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10769325494766235}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.851714015007019},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.811970591545105},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7765573859214783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459176182746887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7366752028465271},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.7006566524505615},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5964145660400391},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.572716474533081},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13686245679855347},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10769325494766235},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":2,"locations":[{"id":"doi:10.1109/icassp.2011.5947406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947406","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50139571","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100622329","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"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":14,"referenced_works":["https://openalex.org/W12391643","https://openalex.org/W81803013","https://openalex.org/W300119222","https://openalex.org/W1872605741","https://openalex.org/W1926768285","https://openalex.org/W1980644794","https://openalex.org/W1984905644","https://openalex.org/W1996550570","https://openalex.org/W2038757250","https://openalex.org/W2049686551","https://openalex.org/W2092910593","https://openalex.org/W6600532773","https://openalex.org/W6603361712","https://openalex.org/W6610697106"],"related_works":["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","https://openalex.org/W2535215250","https://openalex.org/W1537411440","https://openalex.org/W2024201202"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,132],"technique":[4,26,113],"for":[5],"improving":[6],"tone":[7,77,123],"correctness":[8,78,124],"in":[9,35,79],"Thai":[10],"speech":[11,22,54,64,127,135],"synthesis":[12],"based":[13,95],"on":[14,96],"an":[15,39],"average":[16],"voice":[17],"model":[18],"trained":[19],"with":[20],"nonprofessional":[21,138],"corpus.":[23],"The":[24],"proposed":[25,112],"utilizes":[27],"quantized":[28,92],"F0":[29,41,67,93],"symbols":[30,94],"as":[31],"the":[32,46,61,74,91,111,118,122],"tonal":[33,87],"context":[34,48,88],"order":[36],"to":[37,59],"obtain":[38],"appropriate":[40],"model.":[42],"With":[43],"this":[44,57],"technique,":[45],"prosodic":[47],"can":[49,114],"be":[50],"extracted":[51],"from":[52,70],"real":[53],"directly":[55],"and":[56,66,76,98,106],"leads":[58],"prevent":[60],"inconsistency":[62],"between":[63],"data":[65,136],"labels":[68],"generated":[69],"transcription,":[71],"which":[72],"affects":[73],"naturalness":[75,119],"synthetic":[80,126],"speech.":[81],"We":[82],"examine":[83],"two":[84],"types":[85],"of":[86,103,125,130,137],"labeling":[89],"using":[90,131],"phone":[97],"sub-phone":[99],"boundaries.":[100],"Experimental":[101],"results":[102],"both":[104],"objective":[105],"subjective":[107],"tests":[108],"show":[109],"that":[110],"improve":[115],"not":[116],"only":[117],"but":[120],"also":[121],"under":[128],"condition":[129],"small":[133],"amount":[134],"target":[139],"speakers.":[140]},"counts_by_year":[{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}