{"id":"https://openalex.org/W2473236733","doi":"https://doi.org/10.21437/interspeech.2016-487","title":"Waveform Generation Based on Signal Reshaping for Statistical Parametric Speech Synthesis","display_name":"Waveform Generation Based on Signal Reshaping for Statistical Parametric Speech Synthesis","publication_year":2016,"publication_date":"2016-08-28","ids":{"openalex":"https://openalex.org/W2473236733","doi":"https://doi.org/10.21437/interspeech.2016-487","mag":"2473236733"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-487","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/d1225182-a5c0-492f-9481-8a9eaaefede8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015826496","display_name":"Felipe Espic","orcid":null},"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":"Felipe Espic","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"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":"Cassia Valentini-Botinhao","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102765381","display_name":"Zhizheng Wu","orcid":"https://orcid.org/0009-0001-1192-9857"},"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":"Zhizheng Wu","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"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":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2263","last_page":"2267"},"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":0.9998000264167786,"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":0.992900013923645,"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/computer-science","display_name":"Computer science","score":0.7599250078201294},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7208735942840576},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7125481367111206},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6323411464691162},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6256431341171265},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.601740300655365},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5517850518226624},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.4644562900066376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1185624897480011},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1028423011302948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7599250078201294},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7208735942840576},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7125481367111206},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6323411464691162},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6256431341171265},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.601740300655365},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5517850518226624},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.4644562900066376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1185624897480011},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1028423011302948},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2016-487","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/d1225182-a5c0-492f-9481-8a9eaaefede8","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d1225182-a5c0-492f-9481-8a9eaaefede8","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Espic, F, Valentini Botinhao, C, Wu, Z & King, S 2016, Waveform generation based on signal reshaping for statistical parametric speech synthesis. in Interspeech 2016. Interspeech, San Francisco, United States, pp. 2263-2267, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-487","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/d1225182-a5c0-492f-9481-8a9eaaefede8","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/d1225182-a5c0-492f-9481-8a9eaaefede8","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/d1225182-a5c0-492f-9481-8a9eaaefede8","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d1225182-a5c0-492f-9481-8a9eaaefede8","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Espic, F, Valentini Botinhao, C, Wu, Z & King, S 2016, Waveform generation based on signal reshaping for statistical parametric speech synthesis. in Interspeech 2016. Interspeech, San Francisco, United States, pp. 2263-2267, Interspeech 2016, San Francisco, United States, 8/09/16. https://doi.org/10.21437/Interspeech.2016-487","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W167578630","https://openalex.org/W1544516254","https://openalex.org/W1563645159","https://openalex.org/W1601809792","https://openalex.org/W1931958196","https://openalex.org/W1963637322","https://openalex.org/W2049686551","https://openalex.org/W2066999516","https://openalex.org/W2089935964","https://openalex.org/W2091743772","https://openalex.org/W2093450784","https://openalex.org/W2108048146","https://openalex.org/W2115039802","https://openalex.org/W2129142580","https://openalex.org/W2129703931","https://openalex.org/W2141684970","https://openalex.org/W2151890809","https://openalex.org/W2188827208","https://openalex.org/W2398742733","https://openalex.org/W2401318443","https://openalex.org/W2406009315","https://openalex.org/W2406009389","https://openalex.org/W2408190184","https://openalex.org/W2605320104","https://openalex.org/W2916535084","https://openalex.org/W4235154690"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W2176409448","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2424423710","https://openalex.org/W2039489009"],"abstract_inverted_index":{"We":[0,23],"propose":[1],"a":[2,95],"new":[3],"paradigm":[4],"of":[5,27,31,42,55,118,132],"waveform":[6],"generation":[7],"for":[8,139],"Statistical":[9],"Parametric":[10],"Speech":[11],"Synthesis":[12],"that":[13,25,36,150],"is":[14,35,51,92,99,121],"based":[15],"on":[16],"neither":[17],"source-filter":[18,113],"separation":[19],"nor":[20],"sinusoidal":[21],"modelling.":[22],"suggest":[24],"one":[26,142,145],"the":[28,43,64,83,103,108,119,151,157],"main":[29],"problems":[30],"current":[32],"vocoding":[33],"techniques":[34],"they":[37],"perform":[38],"an":[39,52],"extreme":[40],"decomposition":[41],"speech":[44,91],"signal":[45],"into":[46],"source":[47],"and":[48,74,80,86,126,144],"filter,":[49],"which":[50,98],"underlying":[53],"cause":[54],"\u201cbuzziness\u201d,":[56],"\u201cmusical":[57],"artifacts\u201d,":[58],"or":[59],"\u201c":[60],"muffled":[61],"sound\u201d":[62],"in":[63],"synthetic":[65],"speech.":[66],"The":[67,147],"proposed":[68,152],"method":[69,120,153],"avoids":[70],"making":[71],"unnecessary":[72],"assumptions":[73],"decompositions":[75],"as":[76,78,88,94],"far":[77],"possible,":[79],"uses":[81],"only":[82],"spectral":[84],"envelope":[85],"F0":[87],"parameters.":[89,166],"Prerecorded":[90],"used":[93],"base":[96],"signal,":[97],"\u201creshaped\u201d":[100],"to":[101,155],"match":[102],"acoustic":[104,165],"specification":[105],"predicted":[106],"by":[107],"statistical":[109],"model,":[110],"without":[111],"any":[112],"decomposition.":[114],"A":[115],"detailed":[116],"description":[117],"presented,":[122],"including":[123],"implementation":[124],"details":[125],"adjustments.":[127],"Subjective":[128],"listening":[129],"test":[130],"evaluations":[131],"complete":[133],"DNN-based":[134],"text-to-speech":[135],"systems":[136],"were":[137],"conducted":[138],"two":[140],"voices:":[141],"female":[143],"male.":[146],"results":[148],"show":[149],"tends":[154],"outperform":[156],"state-of-theart":[158],"standard":[159],"vocoder":[160],"STRAIGHT,":[161],"whilst":[162],"using":[163],"fewer":[164]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}