{"id":"https://openalex.org/W2276892362","doi":"https://doi.org/10.21437/interspeech.2014-180","title":"An investigation of the application of dynamic sinusoidal models to statistical parametric speech synthesis","display_name":"An investigation of the application of dynamic sinusoidal models to statistical parametric speech synthesis","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2276892362","doi":"https://doi.org/10.21437/interspeech.2014-180","mag":"2276892362"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-180","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/1180ad1b-95b2-4aaa-9b3a-5436a760762a","any_repository_has_fulltext":true},"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":true,"raw_author_name":"Qiong Hu","raw_affiliation_strings":["University of Edinburgh,"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110289715","display_name":"Ranniery Maia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ranniery Maia","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055415493","display_name":"Korin Richmond","orcid":"https://orcid.org/0000-0003-1450-8270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Korin Richmond","raw_affiliation_strings":["School of Informatics, Institute of Language, Cognition and Computation"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Institute of Language, Cognition and Computation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics, Institute of Language, Cognition and Computation"],"affiliations":[{"raw_affiliation_string":"School of Informatics, Institute of Language, Cognition and Computation","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071418947","display_name":"Javier Latorre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Latorre","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5032437290"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":2.5321,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.9154717,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"780","last_page":"784"},"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":0.9986000061035156,"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":0.7819421887397766},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.7775657176971436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6584402322769165},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6516675353050232},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6400476694107056},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5747591257095337},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.47928112745285034},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.43308234214782715},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.414715051651001},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41451597213745117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27320289611816406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23411959409713745},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.14296039938926697},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1298016905784607},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09513998031616211}],"concepts":[{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7819421887397766},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.7775657176971436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6584402322769165},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6516675353050232},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6400476694107056},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5747591257095337},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.47928112745285034},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.43308234214782715},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.414715051651001},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41451597213745117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27320289611816406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23411959409713745},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.14296039938926697},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1298016905784607},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09513998031616211},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2014-180","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/1180ad1b-95b2-4aaa-9b3a-5436a760762a","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.research.ed.ac.uk/en/publications/1180ad1b-95b2-4aaa-9b3a-5436a760762a","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/1180ad1b-95b2-4aaa-9b3a-5436a760762a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/1180ad1b-95b2-4aaa-9b3a-5436a760762a","pdf_url":"https://www.research.ed.ac.uk/en/publications/1180ad1b-95b2-4aaa-9b3a-5436a760762a","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":"Hu, Q, Stylianou, Y, Maia, R, Richmond, K, Yamagishi, J & Latorre, J 2014, An investigation of the application of dynamic sinusoidal models to statistical parametric speech synthesis. in Interspeech 2014. pp. 780-784. < http://www.isca-speech.org/archive/interspeech_2014/i14_0780.html >","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.720.651","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.720.651","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/2014/Q_Interspeech14.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/1180ad1b-95b2-4aaa-9b3a-5436a760762a","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.research.ed.ac.uk/en/publications/1180ad1b-95b2-4aaa-9b3a-5436a760762a","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2276892362.pdf","grobid_xml":"https://content.openalex.org/works/W2276892362.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W68089216","https://openalex.org/W95551363","https://openalex.org/W111544860","https://openalex.org/W175280642","https://openalex.org/W1535737202","https://openalex.org/W1600722501","https://openalex.org/W1601809792","https://openalex.org/W1861150963","https://openalex.org/W1968944773","https://openalex.org/W1993822631","https://openalex.org/W2000513720","https://openalex.org/W2042691334","https://openalex.org/W2066999516","https://openalex.org/W2074854222","https://openalex.org/W2081096848","https://openalex.org/W2145575463","https://openalex.org/W2150658333","https://openalex.org/W2154920538","https://openalex.org/W2231075402","https://openalex.org/W2286166914","https://openalex.org/W2400063444","https://openalex.org/W2402513802"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948","https://openalex.org/W2160511961","https://openalex.org/W2758163923"],"abstract_inverted_index":{"This":[0],"paper":[1],"applies":[2],"a":[3,38,70,79],"dynamic":[4,28,39],"sinusoidal":[5,40],"synthesis":[6,12],"model":[7,41],"to":[8,21,44,52,78,86,104],"statistical":[9,34,100],"parametric":[10],"speech":[11],"(HTS).":[13],"For":[14],"this,":[15],"we":[16],"utilise":[17],"regularised":[18],"cepstral":[19,60],"coefficients":[20],"represent":[22],"both":[23],"the":[24,54],"static":[25],"amplitude":[26],"and":[27],"slope":[29],"of":[30,56,74],"selected":[31,76],"sinusoids":[32,58,75],"for":[33,59],"modelling.":[35],"During":[36],"synthesis,":[37],"is":[42,50,102],"used":[43],"reconstruct":[45],"speech.":[46],"A":[47,90],"preference":[48],"test":[49,95],"conducted":[51],"compare":[53],"selection":[55],"different":[57],"representation.":[61],"Our":[62],"results":[63],"show":[64],"that":[65,97],"when":[66],"integrated":[67],"with":[68],"HTS,":[69],"relatively":[71],"small":[72],"number":[73],"according":[77],"perceptual":[80],"criterion":[81],"can":[82],"produce":[83],"quality":[84],"comparable":[85],"using":[87,106],"all":[88],"harmonics.":[89],"Mean":[91],"Opinion":[92],"Score":[93],"(MOS)":[94],"shows":[96],"our":[98],"proposed":[99],"system":[101],"preferred":[103],"one":[105],"mel-cepstra":[107],"from":[108],"pitch":[109],"synchronous":[110],"spectral":[111],"analysis.":[112]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}