{"id":"https://openalex.org/W2749609415","doi":"https://doi.org/10.21437/interspeech.2017-1647","title":"Direct Modelling of Magnitude and Phase Spectra for Statistical Parametric Speech Synthesis","display_name":"Direct Modelling of Magnitude and Phase Spectra for Statistical Parametric Speech Synthesis","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2749609415","doi":"https://doi.org/10.21437/interspeech.2017-1647","mag":"2749609415"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1647","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/24276b58-4312-4373-bb7a-9457448877df","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":true,"raw_author_name":"Felipe Espic","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"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/A5112271855","display_name":"C\u00e1ssia Valentini Botinh\u00e3o","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":"Cassia Valentini Botinhao","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, UK"],"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"],"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":3,"corresponding_author_ids":["https://openalex.org/A5015826496"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":3.5309,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.94286703,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1383","last_page":"1387"},"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":0.9994999766349792,"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":0.9954000115394592,"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/parametric-statistics","display_name":"Parametric statistics","score":0.7092288136482239},{"id":"https://openalex.org/keywords/magnitude","display_name":"Magnitude (astronomy)","score":0.6782904863357544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5865468978881836},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5028807520866394},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4868130385875702},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.4391818940639496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3407527208328247},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.23795253038406372},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2038724720478058},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1956329345703125},{"id":"https://openalex.org/keywords/astrophysics","display_name":"Astrophysics","score":0.06637760996818542}],"concepts":[{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.7092288136482239},{"id":"https://openalex.org/C126691448","wikidata":"https://www.wikidata.org/wiki/Q2028919","display_name":"Magnitude (astronomy)","level":2,"score":0.6782904863357544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5865468978881836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5028807520866394},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4868130385875702},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.4391818940639496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3407527208328247},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.23795253038406372},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2038724720478058},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1956329345703125},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.06637760996818542},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-1647","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/24276b58-4312-4373-bb7a-9457448877df","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/24276b58-4312-4373-bb7a-9457448877df","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 calder\u00f3n, F, Valentini Botinhao, C & King, S 2017, Direct Modelling of Magnitude and Phase Spectra for Statistical Parametric Speech Synthesis. in Interspeech 2017. Interspeech, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-1647","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/24276b58-4312-4373-bb7a-9457448877df","is_oa":false,"landing_page_url":"https://www.isca-speech.org/archive/Interspeech_2017/abstracts/1647.html","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/24276b58-4312-4373-bb7a-9457448877df","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/24276b58-4312-4373-bb7a-9457448877df","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 calder\u00f3n, F, Valentini Botinhao, C & King, S 2017, Direct Modelling of Magnitude and Phase Spectra for Statistical Parametric Speech Synthesis. in Interspeech 2017. Interspeech, Interspeech 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-1647","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W200094172","https://openalex.org/W795690926","https://openalex.org/W1527535554","https://openalex.org/W1543299179","https://openalex.org/W1544516254","https://openalex.org/W1550888325","https://openalex.org/W1600722501","https://openalex.org/W1601809792","https://openalex.org/W1927394876","https://openalex.org/W2020024436","https://openalex.org/W2020666361","https://openalex.org/W2049686551","https://openalex.org/W2074854222","https://openalex.org/W2102003408","https://openalex.org/W2141684970","https://openalex.org/W2149572519","https://openalex.org/W2276892362","https://openalex.org/W2286166914","https://openalex.org/W2338186431","https://openalex.org/W2395849284","https://openalex.org/W2400319678","https://openalex.org/W2473236733","https://openalex.org/W2519091744","https://openalex.org/W2598638573","https://openalex.org/W2949382160","https://openalex.org/W2964060510"],"related_works":["https://openalex.org/W2376418092","https://openalex.org/W2072983018","https://openalex.org/W1016952678","https://openalex.org/W2257644995","https://openalex.org/W4311345787","https://openalex.org/W2188141918","https://openalex.org/W3185336960","https://openalex.org/W2042652790","https://openalex.org/W2257646557","https://openalex.org/W127416991"],"abstract_inverted_index":{"We":[0,153],"propose":[1],"a":[2,81,128],"simple":[3,72],"new":[4],"representation":[5],"for":[6,140],"the":[7,42,52,61,86,120,132,146,151],"FFT":[8],"spectrum":[9],"tailored":[10],"to":[11,40,157,162],"statistical":[12],"parametric":[13],"speech":[14,43,116],"synthesis.":[15],"It":[16,93],"consists":[17],"of":[18,66],"four":[19],"feature":[20,34],"streams":[21],"that":[22],"describe":[23],"magnitude,":[24],"phase":[25,104],"and":[26,63,73,77,96,114,139,143],"fundamental":[27],"frequency":[28],"using":[29,119,131],"real":[30],"numbers.":[31],"The":[32,69],"proposed":[33,147],"extraction":[35],"method":[36,70,148],"does":[37],"not":[38],"attempt":[39],"decompose":[41],"structure":[44],"(e.g.,":[45],"into":[46],"source+filter":[47],"or":[48,100],"harmonics+noise).":[49],"By":[50],"avoiding":[51],"simplifications":[53],"inherent":[54],"in":[55,90],"decomposition,":[56],"we":[57],"can":[58,78],"dramatically":[59],"reduce":[60],"\u201cphasiness\u201d":[62],"\u201cbuzziness\u201d":[64],"typical":[65,89],"most":[67],"vocoders.":[68],"uses":[71],"computationally":[74],"cheap":[75],"operations":[76],"operate":[79],"at":[80],"lower":[82],"frame":[83],"rate":[84],"than":[85],"200":[87],"frames-per-second":[88],"many":[91],"systems.":[92],"avoids":[94],"heuristics":[95],"methods":[97],"requiring":[98],"approximate":[99],"iterative":[101],"solutions,":[102],"including":[103],"unwrapping.<br/>Two":[105],"DNN-based":[106],"acoustic":[107],"models":[108],"were":[109,125],"built":[110],"-":[111,118],"from":[112],"male":[113,142],"female":[115,144],"data":[117],"Merlin":[121],"toolkit.":[122],"Subjective":[123],"comparisons":[124],"made":[126],"with":[127],"state-of-the-art":[129],"baseline,":[130],"STRAIGHT":[133],"vocoder.":[134],"In":[135],"all":[136],"variants":[137],"tested,":[138],"both":[141],"voices,":[145],"substantially":[149],"outperformed":[150],"baseline.":[152],"provide":[154],"source":[155],"code":[156],"enable":[158],"our":[159],"complete":[160],"system":[161],"be":[163],"replicated.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":9}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}