{"id":"https://openalex.org/W2034202652","doi":"https://doi.org/10.1109/icassp.2013.6639194","title":"HMM-based expressive speech synthesis based on phrase-level F0 context labeling","display_name":"HMM-based expressive speech synthesis based on phrase-level F0 context labeling","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2034202652","doi":"https://doi.org/10.1109/icassp.2013.6639194","mag":"2034202652"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5042527524","display_name":"Yu Maeno","orcid":"https://orcid.org/0000-0001-7754-0054"},"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":"Yu Maeno","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, 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, Japan","Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","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, Japan","Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","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, Japan","Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdiscipl. Grad. Sch. of Sci. & Eng., Tokyo Inst. of Technol., Tokyo, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068604686","display_name":"Yusuke Ijima","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Ijima","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan","NTT Media Intell. Labs., NTT Corp., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Media Intell. Labs., NTT Corp., Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035788151","display_name":"Hideharu Nakajima","orcid":"https://orcid.org/0000-0001-8320-7442"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideharu Nakajima","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan","NTT Media Intell. Labs., NTT Corp., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Media Intell. Labs., NTT Corp., Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102842694","display_name":"Hideyuki Mizuno","orcid":"https://orcid.org/0000-0002-2591-7152"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideyuki Mizuno","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan","NTT Media Intell. Labs., NTT Corp., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Media Intell. Labs., NTT Corp., Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082610849","display_name":"Osamu Yoshioka","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Osamu Yoshioka","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation, Japan","NTT Media Intell. Labs., NTT Corp., Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Media Intell. Labs., NTT Corp., Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9765,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88416797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7859","last_page":"7863"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.996999979019165,"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":0.9962999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.8021335601806641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7589772343635559},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7259896993637085},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6791502237319946},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.674475908279419},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.602279543876648},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.479882150888443},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47744446992874146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4669196605682373},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4463450610637665},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07519274950027466}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8021335601806641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7589772343635559},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7259896993637085},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6791502237319946},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.674475908279419},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.602279543876648},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.479882150888443},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47744446992874146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4669196605682373},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4463450610637665},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07519274950027466},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2013.6639194","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639194","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.47999998927116394,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1963627370","https://openalex.org/W2049686551","https://openalex.org/W2085013480","https://openalex.org/W2093265061","https://openalex.org/W2156146072","https://openalex.org/W2294232014","https://openalex.org/W2401700297","https://openalex.org/W3176415168","https://openalex.org/W6798352252"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W2039546652","https://openalex.org/W2025614924","https://openalex.org/W2294335174","https://openalex.org/W2097963413","https://openalex.org/W3145575561","https://openalex.org/W2001275470","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,92,112],"technique":[4,105],"for":[5,38],"adding":[6],"more":[7],"prosodic":[8],"variations":[9],"to":[10,106],"the":[11,27,39,45,53,74,96,101,108,115,125,131,135,139,146],"synthetic":[12,36,56],"speech":[13,17,37,57,89],"in":[14],"HMM-based":[15],"expressive":[16],"synthesis.":[18],"We":[19,77],"create":[20],"novel":[21],"phrase-level":[22],"F0":[23,31,50,109,117,141],"context":[24,142],"labels":[25,143],"from":[26,145],"residual":[28],"information":[29],"of":[30,47,70,103,119],"features":[32],"between":[33,52],"original":[34,54,116],"and":[35,55,68,81,86],"training":[40],"data.":[41],"Specifically,":[42],"we":[43,99,128],"classify":[44],"difference":[46],"average":[48],"log":[49],"values":[51],"into":[58],"three":[59],"classes":[60],"which":[61],"have":[62],"perceptual":[63],"meanings,":[64],"i.e.,":[65],"high,":[66],"neutral,":[67],"low":[69],"relative":[71],"pitch":[72,136],"at":[73],"phrase":[75],"level.":[76],"evaluate":[78],"both":[79],"ideal":[80,97],"practical":[82,126],"cases":[83],"using":[84],"appealing":[85],"fairy":[87],"tale":[88],"recorded":[90],"under":[91,111],"realistic":[93],"condition.":[94],"In":[95,124],"case,":[98,127],"examine":[100],"potential":[102],"our":[104],"modify":[107,134],"patterns":[110],"condition":[113],"where":[114],"contours":[118],"test":[120],"sentences":[121],"are":[122],"known.":[123],"show":[129],"how":[130],"users":[132],"intuitively":[133],"by":[137],"changing":[138],"initial":[140],"obtained":[144],"input":[147],"text.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}