{"id":"https://openalex.org/W2429907341","doi":"https://doi.org/10.1109/taslp.2016.2580298","title":"Efficient Implementation of Global Variance Compensation for Parametric Speech Synthesis","display_name":"Efficient Implementation of Global Variance Compensation for Parametric Speech Synthesis","publication_year":2016,"publication_date":"2016-06-13","ids":{"openalex":"https://openalex.org/W2429907341","doi":"https://doi.org/10.1109/taslp.2016.2580298","mag":"2429907341"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2580298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2580298","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Department of Communication Engineering, Graduate School of Engineering, Tohoku University, Sendai, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5403-0019","affiliations":[{"raw_affiliation_string":"Department of Communication Engineering, Graduate School of Engineering, Tohoku University, Sendai, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5103144936"],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":null,"apc_paid":null,"fwci":2.1655,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90478821,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"24","issue":"10","first_page":"1694","last_page":"1704"},"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":0.9991000294685364,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7971471548080444},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6324289441108704},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6212030053138733},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6154294013977051},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5611917972564697},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5087435841560364},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34205496311187744},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3031232953071594},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15923282504081726}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7971471548080444},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6324289441108704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6212030053138733},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6154294013977051},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5611917972564697},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5087435841560364},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34205496311187744},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3031232953071594},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15923282504081726},{"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/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},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2016.2580298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2580298","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3566056850","display_name":null,"funder_award_id":"15H02720","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"},{"id":"https://openalex.org/G8947373618","display_name":"Research of Human-Kind Dialogue System with Recognition and Synthesis of Various Speech Based on State Estimation","funder_award_id":"15H02720","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W157817982","https://openalex.org/W200094172","https://openalex.org/W1564152904","https://openalex.org/W1600722501","https://openalex.org/W1935012542","https://openalex.org/W1963627370","https://openalex.org/W1964420823","https://openalex.org/W1965255698","https://openalex.org/W1979449467","https://openalex.org/W1987992317","https://openalex.org/W1992228106","https://openalex.org/W1995332880","https://openalex.org/W2000513720","https://openalex.org/W2030637102","https://openalex.org/W2042360461","https://openalex.org/W2049686551","https://openalex.org/W2093450784","https://openalex.org/W2094519830","https://openalex.org/W2100140000","https://openalex.org/W2102003408","https://openalex.org/W2106792148","https://openalex.org/W2111194146","https://openalex.org/W2129142580","https://openalex.org/W2143490509","https://openalex.org/W2156453709","https://openalex.org/W2156794882","https://openalex.org/W2166823384","https://openalex.org/W2396043161","https://openalex.org/W2404100688","https://openalex.org/W2406654659","https://openalex.org/W2407039802","https://openalex.org/W3176415168","https://openalex.org/W6606405536","https://openalex.org/W6608156246","https://openalex.org/W6675231551","https://openalex.org/W6675380101","https://openalex.org/W6676358011","https://openalex.org/W6682822505","https://openalex.org/W6713535213","https://openalex.org/W6713652182","https://openalex.org/W6714093102","https://openalex.org/W6798352252","https://openalex.org/W7075637324"],"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/W2535215250","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"This":[0,110],"paper":[1,111],"proposes":[2],"a":[3,55,132,140,146],"simple":[4,133],"and":[5,30,127,134,155,163,187],"efficient":[6],"technique":[7],"for":[8,65],"variance":[9,35,123,174],"compensation":[10,136,175],"to":[11,150,191],"improve":[12],"the":[13,26,42,47,70,78,101,157,172,178],"perceptual":[14],"quality":[15],"of":[16,28,54,80,89,107,117,152,159,185],"synthetic":[17],"speech":[18,21,39,71,154,189,193,196],"in":[19,37,85,91,96,115,183],"parametric":[20],"synthesis.":[22,40],"First,":[23],"we":[24],"analyze":[25],"problem":[27],"spectral":[29],"F0":[31],"enhancement":[32,48],"with":[33,60],"global":[34,141],"(GV)":[36],"HMM-based":[38],"In":[41,99],"conventional":[43,179],"GV-based":[44,180],"parameter":[45,72,165,181],"generation,":[46],"is":[49,104],"achieved":[50],"by":[51],"taking":[52],"account":[53],"GV":[56,62,82,125,128,147],"probability":[57],"density":[58],"function":[59],"fixed":[61,81],"model":[63],"parameters":[64,83],"every":[66],"output":[67],"utterance":[68],"through":[69],"generation":[73,182],"process.":[74],"We":[75,130],"find":[76],"that":[77,144,151,171],"use":[79],"results":[84,169],"much":[86],"smaller":[87],"variations":[88],"GVs":[90,160],"synthesized":[92],"utterances":[93],"than":[94],"those":[95],"natural":[97,153,162,192],"speech.":[98],"addition,":[100],"computational":[102],"cost":[103],"high":[105],"because":[106],"iterative":[108],"optimization.":[109],"examines":[112],"these":[113],"issues":[114],"terms":[116,184],"multiple":[118],"objective":[119,186],"measures":[120],"such":[121],"as":[122],"characteristics,":[124],"distortions,":[126],"correlations.":[129],"propose":[131],"fast":[135],"method":[137],"based":[138],"on":[139],"affine":[142],"transformation":[143],"provides":[145],"distribution":[148],"closer":[149],"improves":[156],"correlation":[158],"between":[161],"generated":[164],"sequences.":[166],"The":[167],"experimental":[168],"demonstrate":[170],"proposed":[173],"methods":[176],"outperform":[177],"subjective":[188],"similarity":[190],"while":[194],"maintaining":[195],"naturalness.":[197]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}