{"id":"https://openalex.org/W2099727438","doi":"https://doi.org/10.1109/icassp.2011.5947404","title":"An optimization algorithm of independent mean and variance parameter tying structures for HMM-based speech synthesis","display_name":"An optimization algorithm of independent mean and variance parameter tying structures for HMM-based speech synthesis","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2099727438","doi":"https://doi.org/10.1109/icassp.2011.5947404","mag":"2099727438"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947404","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nitech.repo.nii.ac.jp/record/3462/files/takaki_ICASSP2011.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"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":"Shinji Takaki","raw_affiliation_strings":["Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","Department of Computer Science and Engineering, Nagoya Institute of Technology, 466-8555 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, 466-8555 Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049909008","display_name":"Keiichiro Oura","orcid":null},"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":"Keiichiro Oura","raw_affiliation_strings":["Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","Department of Computer Science and Engineering, Nagoya Institute of Technology, 466-8555 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, 466-8555 Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"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":"Yoshihiko Nankaku","raw_affiliation_strings":["Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","Department of Computer Science and Engineering, Nagoya Institute of Technology, 466-8555 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, 466-8555 Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"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":["Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","Department of Computer Science and Engineering, Nagoya Institute of Technology, 466-8555 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Nagoya Institute of Technology, 466-8555 Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4700","last_page":"4703"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9926000237464905,"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":0.9839000105857849,"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/tying","display_name":"Tying","score":0.8636213541030884},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.8082313537597656},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7287637591362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6068429946899414},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5119886994361877},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5083073973655701},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4595457911491394},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.45582470297813416},{"id":"https://openalex.org/keywords/mean-shift","display_name":"Mean-shift","score":0.4472379684448242},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44111549854278564},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4254996180534363},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36999595165252686},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29260677099227905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28870949149131775},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.286406010389328}],"concepts":[{"id":"https://openalex.org/C2780938662","wikidata":"https://www.wikidata.org/wiki/Q973710","display_name":"Tying","level":2,"score":0.8636213541030884},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.8082313537597656},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7287637591362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6068429946899414},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5119886994361877},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5083073973655701},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4595457911491394},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.45582470297813416},{"id":"https://openalex.org/C48548287","wikidata":"https://www.wikidata.org/wiki/Q6803557","display_name":"Mean-shift","level":3,"score":0.4472379684448242},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44111549854278564},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4254996180534363},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36999595165252686},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29260677099227905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28870949149131775},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.286406010389328},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2011.5947404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947404","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:irdb.nii.ac.jp:01154:0001435329","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/3462","pdf_url":"https://nitech.repo.nii.ac.jp/record/3462/files/takaki_ICASSP2011.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"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":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2011.","raw_type":"conference paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.668.8499","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.668.8499","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://repo.lib.nitech.ac.jp/bitstream/123456789/2316/1/takaki_ICASSP2011.pdf?origin%3Dpublication_detail","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.669.4082","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.669.4082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://repo.lib.nitech.ac.jp/bitstream/123456789/2316/1/takaki_ICASSP2011.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01154:0001435329","is_oa":true,"landing_page_url":"https://nitech.repo.nii.ac.jp/records/3462","pdf_url":"https://nitech.repo.nii.ac.jp/record/3462/files/takaki_ICASSP2011.pdf","source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"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":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2011.","raw_type":"conference paper"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2099727438.pdf","grobid_xml":"https://content.openalex.org/works/W2099727438.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W35069904","https://openalex.org/W1507900585","https://openalex.org/W1600722501","https://openalex.org/W1963627370","https://openalex.org/W2049686551","https://openalex.org/W2093450784","https://openalex.org/W2115222111","https://openalex.org/W2143361917","https://openalex.org/W2166823384","https://openalex.org/W2396713766","https://openalex.org/W2740537351","https://openalex.org/W3036802551","https://openalex.org/W4301420498","https://openalex.org/W6680838236","https://openalex.org/W6684457288","https://openalex.org/W6712520822","https://openalex.org/W6780476513"],"related_works":["https://openalex.org/W2998037107","https://openalex.org/W1597439699","https://openalex.org/W1569871744","https://openalex.org/W2016024526","https://openalex.org/W2379437105","https://openalex.org/W3139928442","https://openalex.org/W1567336638","https://openalex.org/W954011496","https://openalex.org/W175280642","https://openalex.org/W2688184458"],"abstract_inverted_index":{"This":[0,56],"paper":[1],"proposes":[2],"a":[3,39],"technique":[4,41,101],"for":[5,76],"constructing":[6],"independent":[7],"parameter":[8],"tying":[9,31,46,67],"structures":[10],"of":[11,42,53],"mean":[12,21,43,59,77,91],"and":[13,22,60,78,92],"variance":[14,23,48,61,79,93],"in":[15],"HMM":[16],"based":[17],"speech":[18],"synthesis.":[19],"Conventionally,":[20],"parameters":[24,62,80],"are":[25,81],"assumed":[26],"to":[27],"have":[28,64],"the":[29,51,70,73,88,99,103],"same":[30],"structure.":[32],"However,":[33],"it":[34],"has":[35],"been":[36],"reported":[37],"that":[38,58,98],"clustering":[40],"vectors":[44],"while":[45],"all":[47],"matrices":[49],"improves":[50],"quality":[52],"synthesized":[54],"speech.":[55],"indicates":[57],"should":[63],"different":[65],"optimal":[66],"structures.":[68],"In":[69],"proposed":[71,100],"technique,":[72],"decision":[74],"trees":[75],"simultaneously":[82],"grown":[83],"by":[84],"taking":[85],"into":[86],"account":[87],"dependency":[89],"on":[90],"parameters.":[94],"Experimental":[95],"results":[96],"show":[97],"outperforms":[102],"conventional":[104],"one.":[105]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}