{"id":"https://openalex.org/W2143490509","doi":"https://doi.org/10.1109/icassp.2009.4960511","title":"Trajectory training considering global variance for HMM-based speech synthesis","display_name":"Trajectory training considering global variance for HMM-based speech synthesis","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2143490509","doi":"https://doi.org/10.1109/icassp.2009.4960511","mag":"2143490509"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://naist.repo.nii.ac.jp/records/4650","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan","[Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Japan]"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]},{"raw_affiliation_string":"[Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Japan]","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109097977","display_name":"Steve Young","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Young","raw_affiliation_strings":["Department of Engineering, University of Cambridge, UK","Department of Engineering, University of Cambridge,,UK"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge,,UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078330211"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":3.1614,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92431853,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4025","last_page":"4028"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9969000220298767,"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":0.9943000078201294,"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":0.8856748342514038},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7605558633804321},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6898837089538574},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6159150004386902},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5909774303436279},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.5489948987960815},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5342326164245605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5138657093048096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4732266664505005},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42407771944999695},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3437899649143219},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32059526443481445}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8856748342514038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7605558633804321},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6898837089538574},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6159150004386902},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5909774303436279},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.5489948987960815},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5342326164245605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5138657093048096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4732266664505005},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42407771944999695},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3437899649143219},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32059526443481445},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2009.4960511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783101","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4650","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"conference paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.7906","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.7906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mi.eng.cam.ac.uk/~sjy/papers/toyo09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.158.2582","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.158.2582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://spalab.naist.jp/~tomoki/Tomoki/Conferences/ICASSP2009_GVTrjHMM.pdf","raw_type":"text"},{"id":"pmh:oai:generic.eprints.org:324275","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/324275/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"Conference or Workshop Item"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783101","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4650","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1512429158","https://openalex.org/W1600722501","https://openalex.org/W1979449467","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2111194146","https://openalex.org/W2154920538","https://openalex.org/W2156453709","https://openalex.org/W2296704011","https://openalex.org/W3177989406","https://openalex.org/W4301420498","https://openalex.org/W6630838124","https://openalex.org/W6676358011","https://openalex.org/W6682822505","https://openalex.org/W6697285287","https://openalex.org/W6798679566"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W2535215250","https://openalex.org/W2024201202"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,82,88,99,104,120],"novel":[4],"method":[5,74,85,118],"for":[6,12,91,108],"training":[7,49,57,84,93],"hidden":[8],"Markov":[9],"models":[10,34],"(HMMs)":[11],"use":[13],"in":[14,47,123],"HMM-based":[15],"speech":[16],"synthesis.":[17],"The":[18,72,111],"primary":[19],"goal":[20],"of":[21,126],"HMM":[22],"parameter":[23,109],"optimization":[24,60,101],"is":[25],"to":[26,38,86],"ensure":[27],"that":[28,115],"parameters":[29],"generated":[30],"from":[31],"the":[32,53,56,64,68,76,116,124],"trained":[33],"exhibit":[35],"similar":[36],"properties":[37],"natural":[39],"speech.":[40,128],"In":[41],"this":[42],"paper,":[43],"two":[44],"major":[45],"problems":[46],"conventional":[48],"are":[50],"addressed:":[51],"1)":[52],"inconsistency":[54],"between":[55],"and":[58,62,94,103],"synthesis":[59,95],"criterion;":[61],"2)":[63],"over-smoothing":[65],"caused":[66],"by":[67],"statistical":[69],"modeling":[70],"process.":[71],"proposed":[73,117],"integrates":[75],"global":[77],"variance":[78],"(GV)":[79],"criterion":[80,102],"into":[81],"trajectory":[83],"give":[87],"unified":[89],"framework":[90],"both":[92,98],"which":[96],"provides":[97],"consistent":[100],"closed":[105],"form":[106],"solution":[107],"generation.":[110],"experimental":[112],"results":[113],"demonstrate":[114],"yields":[119],"significant":[121],"improvement":[122],"naturalness":[125],"synthetic":[127]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}