{"id":"https://openalex.org/W2154644810","doi":"https://doi.org/10.1109/icassp.2012.6288940","title":"An F0 modeling technique based on prosodic events for spontaneous speech synthesis","display_name":"An F0 modeling technique based on prosodic events for spontaneous speech synthesis","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2154644810","doi":"https://doi.org/10.1109/icassp.2012.6288940","mag":"2154644810"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100636072/ATD100000413/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024181978","display_name":"Tomoki Koriyama","orcid":"https://orcid.org/0000-0002-8347-5604"},"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":"Tomoki Koriyama","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, 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"]}]},{"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"],"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"]}]},{"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"],"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"]}]}],"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":0.5203,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.636722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"4589","last_page":"4592"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9984999895095825,"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":0.9937000274658203,"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/naturalness","display_name":"Naturalness","score":0.7998937964439392},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7849897146224976},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7821377515792847},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7698068618774414},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.7559267282485962},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7088801860809326},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.637218177318573},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5892247557640076},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5379117131233215},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.5142042636871338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39772045612335205},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.35914528369903564},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32945680618286133},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07597938179969788}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7998937964439392},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7849897146224976},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7821377515792847},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7698068618774414},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.7559267282485962},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7088801860809326},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.637218177318573},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5892247557640076},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5379117131233215},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.5142042636871338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39772045612335205},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.35914528369903564},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32945680618286133},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07597938179969788},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"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/icassp.2012.6288940","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50170158","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100636072","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100636072/ATD100000413/","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":{"id":"pmh:oai:t2r2.star.titech.ac.jp:50170158","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100636072","pdf_url":"http://t2r2.star.titech.ac.jp/rrws/file/CTT100636072/ATD100000413/","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1153145764","display_name":"Research on robust spoken language interfaces for diverse voice variability and expressivity","funder_award_id":"21300063","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2575318995","display_name":"A study on speech diversification techniques based on corpus design for advanced humanoid speech synthesis","funder_award_id":"23700195","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2154644810.pdf","grobid_xml":"https://content.openalex.org/works/W2154644810.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W30677081","https://openalex.org/W59470279","https://openalex.org/W157389678","https://openalex.org/W162654330","https://openalex.org/W1512429158","https://openalex.org/W1600722501","https://openalex.org/W1974555773","https://openalex.org/W2039800941","https://openalex.org/W2042600255","https://openalex.org/W2049686551","https://openalex.org/W2106792148","https://openalex.org/W2109938215","https://openalex.org/W2395956841","https://openalex.org/W3034729383","https://openalex.org/W6601230047","https://openalex.org/W6602426571","https://openalex.org/W6606443073","https://openalex.org/W6606697926","https://openalex.org/W6630838124","https://openalex.org/W6712130680","https://openalex.org/W6779469704","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W1965454423","https://openalex.org/W2028501571","https://openalex.org/W4391272374","https://openalex.org/W2052542215","https://openalex.org/W2036564641","https://openalex.org/W2476379844","https://openalex.org/W1984347656","https://openalex.org/W2535215250","https://openalex.org/W1489682032"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3],"technique":[4,94],"for":[5,15],"effective":[6],"modeling":[7,21],"of":[8,26,48,58,69,72,100,107],"F0":[9],"contours":[10],"using":[11,85],"prosodic-event-based":[12],"HMM":[13],"units":[14],"HMM-based":[16],"spontaneous":[17,86],"speech":[18,88],"synthesis.":[19],"The":[20,80],"unit":[22,62],"corresponds":[23],"to":[24,65,76],"one":[25,49],"prosodic":[27,46],"event":[28],"segments":[29],"such":[30],"as":[31],"pitch":[32,37,41],"falling":[33],"by":[34,39],"accent":[35],"and":[36,82],"rising":[38],"boundary":[40],"movement":[42],"(BPM).":[43],"Since":[44],"the":[45,56,60,67,92,98,105,108],"events":[47],"phrase":[50],"are":[51],"generally":[52],"less":[53],"frequent":[54],"than":[55],"changes":[57],"phonemes,":[59],"proposed":[61,93],"is":[63],"expected":[64],"reduce":[66,97],"number":[68,99],"model":[70,101],"parameters":[71,102],"F0,":[73],"which":[74],"leads":[75],"robust":[77],"parameter":[78],"estimation.":[79],"objective":[81],"subjective":[83],"experiments":[84],"conversational":[87],"data":[89],"show":[90],"that":[91],"can":[95],"significantly":[96],"while":[103],"keeping":[104],"naturalness":[106],"synthetic":[109],"speech.":[110]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}