{"id":"https://openalex.org/W2150000736","doi":"https://doi.org/10.1109/icassp.2008.4518520","title":"Performance evaluation of the speaker-independent HMM-based speech synthesis system “HTS 2007” for the Blizzard Challenge 2007","display_name":"Performance evaluation of the speaker-independent HMM-based speech synthesis system “HTS 2007” for the Blizzard Challenge 2007","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2150000736","doi":"https://doi.org/10.1109/icassp.2008.4518520","mag":"2150000736"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518520","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"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":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://era.ed.ac.uk/bitstream/1842/3831/1/Lecture.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"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, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003420204","display_name":"Heiga Zen","orcid":"https://orcid.org/0000-0002-8959-5471"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Heiga Zen","raw_affiliation_strings":["Nagoya Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Nagoya Institute of Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7621,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85823048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3957","last_page":"3960"},"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":0.9955000281333923,"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":0.9908999800682068,"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/speech-recognition","display_name":"Speech recognition","score":0.6786392331123352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6206568479537964},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6186820864677429}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6786392331123352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6206568479537964},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6186820864677429}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2008.4518520","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518520","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"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":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:era.ed.ac.uk:1842/3831","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3831","pdf_url":"https://era.ed.ac.uk/bitstream/1842/3831/1/Lecture.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:library.naist.jp:10061/8070","is_oa":true,"landing_page_url":"http://hdl.handle.net/10061/8070","pdf_url":null,"source":{"id":"https://openalex.org/S4377196843","display_name":"NAIST Digital Library (Nara Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I75917431","host_organization_name":"Nara Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I75917431"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/dabb2e93-158d-49b4-9394-38a19959b6dc","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/dabb2e93-158d-49b4-9394-38a19959b6dc","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yamagishi, J, Nose, T, Zen, H, Toda, T & Tokuda, K 2008, Performance Evaluation of The Speaker-Independent HMM-based Speech Synthesis System \"HTS-2007\" for the Blizzard Challenge 2007. in Proc. ICASSP 2008. pp. 3957-3960. https://doi.org/10.1109/ICASSP.2008.4518520","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/dabb2e93-158d-49b4-9394-38a19959b6dc","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/dabb2e93-158d-49b4-9394-38a19959b6dc","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:era.ed.ac.uk:1842/3831","is_oa":true,"landing_page_url":"http://hdl.handle.net/1842/3831","pdf_url":"https://era.ed.ac.uk/bitstream/1842/3831/1/Lecture.pdf","source":{"id":"https://openalex.org/S7407055182","display_name":"ERA","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2150000736.pdf","grobid_xml":"https://content.openalex.org/works/W2150000736.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W300119222","https://openalex.org/W1600722501","https://openalex.org/W1984905644","https://openalex.org/W2000513720","https://openalex.org/W2009417200","https://openalex.org/W2042691334","https://openalex.org/W2049686551","https://openalex.org/W2106554350","https://openalex.org/W2106792148","https://openalex.org/W2145575463","https://openalex.org/W2149175990","https://openalex.org/W2150617255","https://openalex.org/W2159150199","https://openalex.org/W2165856656","https://openalex.org/W2168584209","https://openalex.org/W2400063444","https://openalex.org/W2915628810","https://openalex.org/W4395452447","https://openalex.org/W6610697106","https://openalex.org/W6683730234","https://openalex.org/W6684311649","https://openalex.org/W6684513021","https://openalex.org/W6759752890","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"a":[3],"speaker-independent/adaptive":[4],"HMM-based":[5],"speech":[6,62,72,87],"synthesis":[7],"system":[8,56],"developed":[9],"for":[10],"the":[11,54],"Blizzard":[12],"Challenge":[13],"2007.":[14],"The":[15],"new":[16,55],"system,":[17],"named":[18],"\u201cHTS-2007\u201d,":[19],"employs":[20],"speaker":[21],"adaptation":[22],"(CSMAPLR+MAP),":[23],"feature-space":[24],"adaptive":[25],"training,":[26],"mixed-gender":[27],"modeling,":[28],"and":[29,74],"full-covariance":[30],"modeling":[31],"using":[32],"CSMAPLR":[33],"transforms,":[34],"in":[35,45],"addition":[36],"to":[37],"several":[38],"other":[39],"techniques":[40],"that":[41,53,64,75],"have":[42],"proved":[43],"effective":[44],"our":[46],"previous":[47],"systems.":[48],"Subjective":[49],"evaluation":[50],"results":[51],"show":[52],"generates":[57],"significantly":[58],"better":[59],"quality":[60],"synthetic":[61],"than":[63],"of":[65,71,86],"speaker-dependent":[66,80],"approaches":[67,81],"with":[68,79],"realistic":[69],"amounts":[70,85],"data,":[73],"it":[76],"bears":[77],"comparison":[78],"even":[82],"when":[83],"large":[84],"data":[88],"are":[89],"available.":[90]},"counts_by_year":[{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2016-06-24T00:00:00"}