{"id":"https://openalex.org/W2034162223","doi":"https://doi.org/10.1109/icassp.2014.6853606","title":"Linear dynamical models in speech synthesis","display_name":"Linear dynamical models in speech synthesis","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2034162223","doi":"https://doi.org/10.1109/icassp.2014.6853606","mag":"2034162223"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5049252564","display_name":"Vassilis Tsiaras","orcid":"https://orcid.org/0000-0002-6677-1946"},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vassilis Tsiaras","raw_affiliation_strings":["Technical University of Crete, School of Electronic and Computer Engineering, Chania, Greece","[Sch. of Electron. & Comput. Eng., Tech. Univ. of Crete, Chania, Greece]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Crete, School of Electronic and Computer Engineering, Chania, Greece","institution_ids":["https://openalex.org/I55741626"]},{"raw_affiliation_string":"[Sch. of Electron. & Comput. Eng., Tech. Univ. of Crete, Chania, Greece]","institution_ids":["https://openalex.org/I55741626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110289715","display_name":"Ranniery Maia","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Ranniery Maia","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031538820","display_name":"Vassilios Diakoloukas","orcid":"https://orcid.org/0000-0002-1030-2892"},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vassilis Diakoloukas","raw_affiliation_strings":["Technical University of Crete, School of Electronic and Computer Engineering, Chania, Greece","[Sch. of Electron. & Comput. Eng., Tech. Univ. of Crete, Chania, Greece]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Crete, School of Electronic and Computer Engineering, Chania, Greece","institution_ids":["https://openalex.org/I55741626"]},{"raw_affiliation_string":"[Sch. of Electron. & Comput. Eng., Tech. Univ. of Crete, Chania, Greece]","institution_ids":["https://openalex.org/I55741626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]},{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]},{"raw_affiliation_string":"Cambridge Res. Lab., Toshiba Res. Eur. Ltd., Cambridge, UK","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030929323","display_name":"Vassilios Digalakis","orcid":"https://orcid.org/0000-0002-1255-8939"},"institutions":[{"id":"https://openalex.org/I55741626","display_name":"Technical University of Crete","ror":"https://ror.org/03f8bz564","country_code":"GR","type":"education","lineage":["https://openalex.org/I55741626"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vassilis Digalakis","raw_affiliation_strings":["Technical University of Crete, School of Electronic and Computer Engineering, Chania, Greece","[Sch. of Electron. & Comput. Eng., Tech. Univ. of Crete, Chania, Greece]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Crete, School of Electronic and Computer Engineering, Chania, Greece","institution_ids":["https://openalex.org/I55741626"]},{"raw_affiliation_string":"[Sch. of Electron. & Comput. Eng., Tech. Univ. of Crete, Chania, Greece]","institution_ids":["https://openalex.org/I55741626"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8458,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.81130674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"300","last_page":"304"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8943739533424377},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7452759742736816},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7289041876792908},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7196946144104004},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6276492476463318},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.45445704460144043},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.4483529329299927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3546399772167206},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13838869333267212}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8943739533424377},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7452759742736816},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7289041876792908},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7196946144104004},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6276492476463318},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.45445704460144043},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.4483529329299927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3546399772167206},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13838869333267212},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853606","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1511967608","https://openalex.org/W1552314771","https://openalex.org/W1576040274","https://openalex.org/W1979449467","https://openalex.org/W1984820788","https://openalex.org/W2083393647","https://openalex.org/W2099932314","https://openalex.org/W2106792148","https://openalex.org/W2116927898","https://openalex.org/W2129142580","https://openalex.org/W2136442985","https://openalex.org/W2149361029","https://openalex.org/W2159027556","https://openalex.org/W2401881555","https://openalex.org/W2615836285","https://openalex.org/W4285719527","https://openalex.org/W6634609852"],"related_works":["https://openalex.org/W2038801705","https://openalex.org/W2028487795","https://openalex.org/W2688184458","https://openalex.org/W2904846757","https://openalex.org/W2289718384","https://openalex.org/W1995675544","https://openalex.org/W2509524819","https://openalex.org/W3127866798","https://openalex.org/W2068427817","https://openalex.org/W1494715773"],"abstract_inverted_index":{"Hidden":[0],"Markov":[1],"models":[2],"(HMMs)":[3],"are":[4,60,143],"becoming":[5],"the":[6,36,39,70,93,105,121],"dominant":[7],"approach":[8],"for":[9,27,125,150],"text-to-speech":[10],"synthesis":[11,52],"(TTS).":[12],"HMMs":[13,59],"provide":[14],"an":[15],"attractive":[16],"acoustic":[17,147],"modeling":[18,148],"scheme":[19],"which":[20,65],"has":[21,53],"been":[22],"exhaustively":[23],"investigated":[24],"and":[25,97,142],"developed":[26],"many":[28],"years.":[29],"Modern":[30],"HMM-based":[31,135],"speech":[32,51,96,126],"synthesizers":[33,132],"have":[34],"approached":[35],"quality":[37],"of":[38,72,87,95,104,112,123,139],"best":[40],"state-of-the-art":[41],"unit":[42],"selection":[43],"systems.":[44],"However,":[45],"we":[46],"believe":[47],"that":[48,130],"statistical":[49,151],"parametric":[50,152],"not":[54,67],"reached":[55],"its":[56],"potential,":[57],"since":[58],"limited":[61],"by":[62],"several":[63],"assumptions":[64],"do":[66],"apply":[68],"to":[69,80,118],"properties":[71],"speech.":[73,107],"We,":[74],"therefore,":[75],"propose":[76],"in":[77,137],"this":[78],"paper":[79],"use":[81],"Linear":[82],"Dynamical":[83],"Models":[84],"(LDMs)":[85],"instead":[86],"HMMs.":[88],"LDMs":[89,124],"can":[90,98,133],"better":[91],"model":[92],"dynamics":[94],"produce":[99],"a":[100,110,144],"naturally":[101],"smoother":[102],"trajectory":[103],"synthesized":[106],"We":[108,128],"perform":[109],"series":[111],"experiments":[113],"using":[114],"different":[115],"system":[116],"configurations":[117],"check":[119],"on":[120],"performance":[122],"synthesis.":[127],"show":[129],"LDM-based":[131],"outperform":[134],"ones":[136],"terms":[138],"cepstral":[140],"distance":[141],"very":[145],"promising":[146],"alternative":[149],"TTS.":[153]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
