{"id":"https://openalex.org/W2408220395","doi":"https://doi.org/10.21437/interspeech.2012-158","title":"Discontinuous observation HMM for prosodic-event-based F0 generation","display_name":"Discontinuous observation HMM for prosodic-event-based F0 generation","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2408220395","doi":"https://doi.org/10.21437/interspeech.2012-158","mag":"2408220395"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-158","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100644237","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":["Tokyo Institute of Technology;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology;","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":["Tokyo Institute of Technology;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology;","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":["Tokyo Institute of Technology;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology;","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":0.26,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54362683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"462","last_page":"465"},"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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/T12031","display_name":"Speech and dialogue systems","score":0.9890999794006348,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7965109348297119},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.727851927280426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6299075484275818},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5820721387863159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40892916917800903},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39125150442123413},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07229655981063843}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7965109348297119},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.727851927280426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6299075484275818},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5820721387863159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40892916917800903},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39125150442123413},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07229655981063843},{"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:10.21437/interspeech.2012-158","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50185811","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100644237","pdf_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100644237","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:50185811","is_oa":true,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100644237","pdf_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100644237","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":[{"score":0.6200000047683716,"display_name":"Climate action","id":"https://metadata.un.org/sdg/13"}],"awards":[{"id":"https://openalex.org/G1573140883","display_name":"Research on advanced robust speech synthesis and its applications to multi-lingual speech communication","funder_award_id":"24300071","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2408220395.pdf","grobid_xml":"https://content.openalex.org/works/W2408220395.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W30677081","https://openalex.org/W1512429158","https://openalex.org/W2049686551","https://openalex.org/W2085245374","https://openalex.org/W2106792148","https://openalex.org/W2395956841"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2157423375"],"abstract_inverted_index":{"This":[0],"paper":[1],"examines":[2],"F0":[3,47,54,60,69,85,114],"modeling":[4,115],"and":[5,66,117],"generation":[6],"techniques":[7,116],"for":[8,75],"spontaneous":[9],"speech":[10],"synthesis.In":[11],"the":[12,21,40,43,64,67,93,103,106,112,119],"previous":[13],"study,":[14],"we":[15,81],"proposed":[16],"a":[17,27,35],"prosodic-unit":[18],"HMM":[19,70,90],"where":[20,92],"synthesis":[22],"unit":[23],"is":[24],"defined":[25],"as":[26,63,98],"segment":[28],"between":[29],"two":[30],"prosodic":[31],"events":[32],"represented":[33],"by":[34,108],"ToBI":[36],"label":[37],"framework.To":[38],"take":[39],"advantage":[41],"of":[42,105],"prosodicunit":[44],"HMM,":[45],"continuous":[46,68],"sequences":[48],"must":[49],"be":[50],"modeled":[51],"from":[52],"discontinuous":[53,88],"data":[55],"including":[56],"unvoiced":[57,94],"regions.The":[58],"conventional":[59,113],"models":[61],"such":[62,76],"MSD-HMM":[65],"are":[71,96],"not":[72],"always":[73],"appropriate":[74],"demand.To":[77],"overcome":[78],"this":[79],"problem,":[80],"propose":[82],"an":[83],"alternative":[84],"model":[86],"named":[87],"observation":[89],"(DO-HMM)":[91],"frames":[95],"regarded":[97],"missing":[99],"data.We":[100],"objectively":[101],"evaluate":[102],"performance":[104],"DO-HMM":[107],"comparing":[109],"it":[110],"with":[111],"discuss":[118],"results.":[120]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}