{"id":"https://openalex.org/W1494715773","doi":"https://doi.org/10.1109/icassp.2015.7178900","title":"Methods for applying dynamic sinusoidal models to statistical parametric speech synthesis","display_name":"Methods for applying dynamic sinusoidal models to statistical parametric speech synthesis","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1494715773","doi":"https://doi.org/10.1109/icassp.2015.7178900","mag":"1494715773"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5032437290","display_name":"Qiong Hu","orcid":"https://orcid.org/0000-0002-7525-1387"},"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":"Qiong Hu","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":["Toshiba Research Europe Ltd, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110289715","display_name":"Ranniery Maia","orcid":null},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Ranniery Maia","raw_affiliation_strings":["Toshiba Research Europe Ltd, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Ltd, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"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":"Korin Richmond","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"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","JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan","The Centre for Speech Technology Research, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3355,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85471473,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"90","issue":null,"first_page":"4889","last_page":"4893"},"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":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.9923999905586243,"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/cepstrum","display_name":"Cepstrum","score":0.8447900414466858},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7517131567001343},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7223175764083862},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6988108158111572},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6857718825340271},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.5833774209022522},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.4996027946472168},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.43417686223983765},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4322616457939148},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.4229351878166199},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3810803294181824},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.26800984144210815},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17517539858818054},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08212250471115112},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07355964183807373}],"concepts":[{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.8447900414466858},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7517131567001343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7223175764083862},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6988108158111572},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6857718825340271},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.5833774209022522},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.4996027946472168},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.43417686223983765},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4322616457939148},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.4229351878166199},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3810803294181824},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.26800984144210815},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17517539858818054},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08212250471115112},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07355964183807373},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178900","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178900","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.715.8009","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.715.8009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2015/IC15_Qiong.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4000000059604645,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2750010394","display_name":null,"funder_award_id":"EP/I027696/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W95551363","https://openalex.org/W111544860","https://openalex.org/W175280642","https://openalex.org/W1600722501","https://openalex.org/W1601809792","https://openalex.org/W1963637322","https://openalex.org/W1968944773","https://openalex.org/W1993822631","https://openalex.org/W2000513720","https://openalex.org/W2042691334","https://openalex.org/W2049686551","https://openalex.org/W2066999516","https://openalex.org/W2074854222","https://openalex.org/W2081096848","https://openalex.org/W2129142580","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2231075402","https://openalex.org/W2276892362","https://openalex.org/W2286166914","https://openalex.org/W2400063444","https://openalex.org/W2402513802","https://openalex.org/W3141097117","https://openalex.org/W6604512307","https://openalex.org/W6636056872","https://openalex.org/W6682221467","https://openalex.org/W6694585905","https://openalex.org/W6696156092","https://openalex.org/W6712610176","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W193702574","https://openalex.org/W1842536210","https://openalex.org/W1494715773","https://openalex.org/W1852231985","https://openalex.org/W2080325429","https://openalex.org/W2184306570","https://openalex.org/W2351647310","https://openalex.org/W2140099343","https://openalex.org/W1524172635","https://openalex.org/W1796893744"],"abstract_inverted_index":{"Sinusoidal":[0],"vocoders":[1],"can":[2,137],"generate":[3,138],"high":[4],"quality":[5,112,140,155],"speech,":[6],"but":[7],"they":[8],"have":[9,108],"not":[10],"been":[11],"extensively":[12],"applied":[13],"to":[14,37,90,104,117,158],"statistical":[15,30],"parametric":[16],"speech":[17,31,154],"synthesis.":[18,42],"This":[19],"paper":[20],"presents":[21],"two":[22,115],"ways":[23],"for":[24,29,96],"using":[25],"dynamic":[26,55,73],"sinusoidal":[27,56],"models":[28],"synthesis,":[32,99],"enabling":[33],"the":[34,44,64,77,85,110,118],"sinusoid":[35],"parameters":[36,92,136,160],"be":[38],"modelled":[39,61],"in":[40,125,149],"HMM-based":[41],"In":[43,63],"first":[45],"method,":[46,66],"features":[47],"extracted":[48],"from":[49,75],"a":[50,80],"fixed-":[51],"and":[52,72],"low-dimensional,":[53],"perception-based":[54],"model":[57],"(PDM)":[58],"are":[59],"statistically":[60],"directly.":[62],"second":[65],"we":[67,83],"convert":[68],"both":[69],"static":[70],"amplitude":[71],"slope":[74],"all":[76],"harmonics":[78],"of":[79,113,151],"signal,":[81],"which":[82],"term":[84],"Harmonic":[86],"Dynamic":[87],"Model":[88],"(HDM),":[89],"intermediate":[91,135,159],"(regularised":[93],"cepstral":[94],"coefficients)":[95],"modelling.":[97],"During":[98],"HDM":[100,133],"is":[101],"then":[102],"used":[103],"reconstruct":[105],"speech.":[106],"We":[107],"compared":[109],"voice":[111],"these":[114],"methods":[116],"STRAIGHT":[119],"cepstrum-based":[120],"vocoder":[121],"with":[122,134],"mixed":[123],"excitation":[124],"formal":[126],"listening":[127],"tests.":[128],"Our":[129],"results":[130],"show":[131],"that":[132],"comparable":[139],"as":[141,162],"STRAIGHT,":[142],"while":[143],"PDM":[144],"direct":[145],"modelling":[146],"seems":[147],"promising":[148],"terms":[150],"producing":[152],"good":[153],"without":[156],"resorting":[157],"such":[161],"cepstra.":[163]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}