{"id":"https://openalex.org/W2524651405","doi":"https://doi.org/10.21437/ssw.2016-11","title":"Development of a statistical parametric synthesis system for operatic singing in German","display_name":"Development of a statistical parametric synthesis system for operatic singing in German","publication_year":2016,"publication_date":"2016-09-13","ids":{"openalex":"https://openalex.org/W2524651405","doi":"https://doi.org/10.21437/ssw.2016-11","mag":"2524651405"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2016-11","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-11","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)","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/271091b0-d8ce-4626-b159-831b5858e26f","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088212404","display_name":"Michael Pucher","orcid":"https://orcid.org/0000-0002-5374-1342"},"institutions":[{"id":"https://openalex.org/I138211613","display_name":"Austrian Academy of Sciences","ror":"https://ror.org/03anc3s24","country_code":"AT","type":"funder","lineage":["https://openalex.org/I138211613"]},{"id":"https://openalex.org/I2800119247","display_name":"Acoustics Research Institute","ror":"https://ror.org/04jd9ff79","country_code":"AT","type":"facility","lineage":["https://openalex.org/I138211613","https://openalex.org/I2800119247"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Michael Pucher","raw_affiliation_strings":["Acoustics Research Institute, Austrian Academy of Sciences, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Acoustics Research Institute, Austrian Academy of Sciences, Vienna, Austria","institution_ids":["https://openalex.org/I138211613","https://openalex.org/I2800119247"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020219878","display_name":"Fernando Villavicencio","orcid":null},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fernando Villavicencio","raw_affiliation_strings":["National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"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":["Centre for Speech Technology Research, University of Edinburgh, UK","National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088212404"],"corresponding_institution_ids":["https://openalex.org/I138211613","https://openalex.org/I2800119247"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.06259778,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"64","last_page":"69"},"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":0.9998999834060669,"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":0.9998000264167786,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7962732911109924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7338917851448059},{"id":"https://openalex.org/keywords/vibrato","display_name":"Vibrato","score":0.7226549386978149},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.7034101486206055},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7025400400161743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6876016855239868},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5906604528427124},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5268389582633972},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5157511830329895},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4502354562282562},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4433751702308655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3221905827522278},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22439587116241455},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.19514045119285583},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.13234910368919373},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10764017701148987}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7962732911109924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7338917851448059},{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.7226549386978149},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.7034101486206055},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7025400400161743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6876016855239868},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5906604528427124},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5268389582633972},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5157511830329895},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4502354562282562},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4433751702308655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3221905827522278},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22439587116241455},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.19514045119285583},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.13234910368919373},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10764017701148987},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":3,"locations":[{"id":"doi:10.21437/ssw.2016-11","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-11","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/271091b0-d8ce-4626-b159-831b5858e26f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/271091b0-d8ce-4626-b159-831b5858e26f","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Pucher, M, Villavicencio, F & Yamagishi, J 2016, Development of a statistical parametric synthesis system for operatic singing in German. in Proceedings of 9th ISCA Speech Synthesis Workshop. International Speech Communication Association, pp. 68-73, 9th ISCA Speech Synthesis Workshop (SSW9), Sunnyvale, California, United States, 13/09/16. https://doi.org/10.21437/SSW.2016-11","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/271091b0-d8ce-4626-b159-831b5858e26f","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/development-of-a-statistical-parametric-synthesis-system-for-operatic-singing-in-german(271091b0-d8ce-4626-b159-831b5858e26f).html","pdf_url":null,"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":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/271091b0-d8ce-4626-b159-831b5858e26f","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/271091b0-d8ce-4626-b159-831b5858e26f","pdf_url":null,"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Pucher, M, Villavicencio, F & Yamagishi, J 2016, Development of a statistical parametric synthesis system for operatic singing in German. in Proceedings of 9th ISCA Speech Synthesis Workshop. International Speech Communication Association, pp. 68-73, 9th ISCA Speech Synthesis Workshop (SSW9), Sunnyvale, California, United States, 13/09/16. https://doi.org/10.21437/SSW.2016-11","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2521286739","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334789","funder_display_name":"Japan Science and Technology Agency"},{"id":"https://openalex.org/G2920681495","display_name":null,"funder_award_id":"(CREST)","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G3007105200","display_name":"Deep architectures for statistical speech synthesis","funder_award_id":"EP/J002526/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3790594077","display_name":"Natural Speech Technology","funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"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"},{"id":"https://openalex.org/G7939917082","display_name":null,"funder_award_id":"P23821-N23","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"}],"funders":[{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W17607154","https://openalex.org/W29794711","https://openalex.org/W1571500165","https://openalex.org/W2048752878","https://openalex.org/W2049686551","https://openalex.org/W2066598518","https://openalex.org/W2076374976","https://openalex.org/W2124097505","https://openalex.org/W2142357540","https://openalex.org/W2150933458","https://openalex.org/W2154920538","https://openalex.org/W2271389969","https://openalex.org/W2408435475","https://openalex.org/W3033433517","https://openalex.org/W4213009134"],"related_works":["https://openalex.org/W2373880408","https://openalex.org/W405661683","https://openalex.org/W2532856746","https://openalex.org/W238390473","https://openalex.org/W2119168266","https://openalex.org/W2978145617","https://openalex.org/W4230480656","https://openalex.org/W2108382268","https://openalex.org/W2097873655","https://openalex.org/W2153098279"],"abstract_inverted_index":{"In":[0],"this":[1,42],"paper":[2],"we":[3,75,131,141],"describe":[4,105],"the":[5,26,73,106,109,112,152,162,168,171,183],"development":[6],"of":[7,25,41,45,94,97,108,122,170],"a":[8,62,133,143],"Hidden":[9],"Markov":[10],"Model":[11],"(HMM)":[12],"based":[13,87,101],"synthesis":[14,28],"system":[15,29,43],"for":[16,30,69],"operatic":[17,78],"singing":[18,79,95,120],"in":[19,33,102,126,182],"German,":[20],"which":[21,57,92],"is":[22,116],"an":[23],"extension":[24],"HMM-based":[27],"popular":[31],"songs":[32],"Japanese":[34],"and":[35,50,54,83,111,156,185],"English":[36],"called":[37],"\u201cSinsy\u201d.":[38],"The":[39],"implementation":[40],"consists":[44,93],"German":[46,63],"text":[47],"analysis,":[48],"lexicon":[49],"Letter-To-Sound":[51],"(LTS)":[52],"conversion,":[53],"syllable":[55],"duplication,":[56],"enables":[58],"us":[59],"to":[60,118],"convert":[61],"MusicXML":[64],"input":[65],"into":[66],"context-dependent":[67],"labels":[68],"acoustic":[70],"modelling.":[71],"<br/>Using":[72],"front-end,":[74],"develop":[76],"two":[77,174],"voices,":[80,86],"female":[81],"mezzo-soprano":[82],"male":[84],"bass":[85],"on":[88],"our":[89],"new":[90],"database,":[91],"data":[96,121],"professional":[98],"opera":[99,124],"singers":[100,125],"Vienna.":[103],"We":[104,166],"details":[107],"database":[110],"recording":[113],"procedure":[114],"that":[115,146,178,187],"used":[117],"acquire":[119],"four":[123],"German.":[127],"<br/>For":[128],"HMM":[129],"training,":[130],"adopt":[132],"singer":[134],"(speaker)-dependent":[135],"training":[136],"procedure.":[137],"For":[138],"duration":[139,155],"modelling":[140,176],"propose":[142],"simple":[144],"method":[145],"hierarchically":[147],"constrains":[148,158],"note":[149,164],"durations":[150,160],"by":[151,161],"overall":[153],"utterance":[154],"then":[157],"phone":[159],"synthesised":[163],"duration.":[165],"evaluate":[167],"performance":[169],"voices":[172],"with":[173],"vibrato":[175],"methods":[177],"have":[179],"been":[180],"proposed":[181],"literature":[184],"show":[186],"HM":[188]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}