{"id":"https://openalex.org/W2516422588","doi":"https://doi.org/10.1109/slt.2016.7846337","title":"Median-based generation of synthetic speech durations using a non-parametric approach","display_name":"Median-based generation of synthetic speech durations using a non-parametric approach","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2516422588","doi":"https://doi.org/10.1109/slt.2016.7846337","mag":"2516422588"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2016.7846337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1608.06134","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Srikanth Ronanki","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":"Srikanth Ronanki","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), The University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), The University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Oliver Watts","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":"Oliver Watts","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), The University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), The University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Simon King","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":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), The University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), The University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":null,"display_name":"Gustav Eje Henter","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":"Gustav Eje Henter","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), The University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), The 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":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"686","last_page":"692"},"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":0.9975000023841858,"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":0.9962000250816345,"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/duration","display_name":"Duration (music)","score":0.8083999752998352},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5679000020027161},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.47119998931884766},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.45969998836517334},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4449000060558319},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.40619999170303345}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.8083999752998352},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5679000020027161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.508899986743927},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.45969998836517334},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.40619999170303345},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34929999709129333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33329999446868896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30320000648498535},{"id":"https://openalex.org/C149717495","wikidata":"https://www.wikidata.org/wiki/Q117806","display_name":"Gamma distribution","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt.2016.7846337","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846337","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1608.06134","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.06134","pdf_url":"https://arxiv.org/pdf/1608.06134","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/e0dc0d22-fb2a-4d33-a23f-9abf5b7346b3","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/e0dc0d22-fb2a-4d33-a23f-9abf5b7346b3","pdf_url":"https://www.research.ed.ac.uk/files/31167775/ronanki2016mediandur.pdf","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":"Ronanki, S, Watts, O, King, S & Henter, G E 2017, Median-based generation of synthetic speech durations using a non-parametric approach. in 2016 IEEE Spoken Language Technology Workshop (SLT). Institute of Electrical and Electronics Engineers, pp. 686-692, 2016 IEEE Spoken Language Technology Workshop, San Diego, California, United States, 13/12/16. https://doi.org/10.1109/SLT.2016.7846337","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1608.06134","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1608.06134","pdf_url":"https://arxiv.org/pdf/1608.06134","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"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"}],"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":25,"referenced_works":["https://openalex.org/W141887692","https://openalex.org/W175280642","https://openalex.org/W1499332833","https://openalex.org/W1576227399","https://openalex.org/W1927421023","https://openalex.org/W2016923030","https://openalex.org/W2066452495","https://openalex.org/W2098372067","https://openalex.org/W2107860279","https://openalex.org/W2127998573","https://openalex.org/W2129142580","https://openalex.org/W2150612204","https://openalex.org/W2154920538","https://openalex.org/W2405144467","https://openalex.org/W2513051195","https://openalex.org/W2964060510","https://openalex.org/W2964301388","https://openalex.org/W6638081404","https://openalex.org/W6675380101","https://openalex.org/W6677973343","https://openalex.org/W6687241212","https://openalex.org/W6712239235","https://openalex.org/W6712610176","https://openalex.org/W6736204136","https://openalex.org/W6748514727"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,16,24,46,50,118,127],"new":[4],"approach":[5,63,120],"to":[6,22,36,110,121],"duration":[7,37,43,122,152],"modelling":[8,38,131],"for":[9,59],"statistical":[10,18],"parametric":[11],"speech":[12],"synthesis":[13,60],"in":[14,65,82,148],"which":[15,40],"recurrent":[17],"model":[19,67,78],"is":[20,98,108,124,143],"trained":[21],"output":[23,88],"phone":[25],"transition":[26],"probability":[27],"at":[28],"each":[29],"timestep":[30],"(acoustic":[31],"frame).":[32],"Unlike":[33],"conventional":[34,105],"approaches":[35,147],"-":[39,61],"assume":[41],"that":[42,57,139],"distributions":[44],"have":[45],"particular":[47],"form":[48],"(e.g.,":[49],"Gaussian)":[51],"and":[52,113,133],"use":[53],"the":[54,72,92,104,140,150],"mean":[55,106],"of":[56,130,153],"distribution":[58,69],"our":[62],"can":[64,79],"principle":[66],"any":[68],"supported":[70],"on":[71,91],"non-negative":[73],"integers.":[74],"Generation":[75],"from":[76],"this":[77],"be":[80],"performed":[81],"many":[83],"ways;":[84],"here":[85],"we":[86],"consider":[87],"generation":[89],"based":[90],"median":[93,97,151],"predicted":[94],"duration.":[95],"The":[96],"more":[99],"typical":[100],"(more":[101],"probable)":[102],"than":[103],"duration,":[107],"robust":[109],"training-data":[111],"irregularities,":[112],"enables":[114],"incremental":[115],"generation.":[116],"Furthermore,":[117],"frame-level":[119],"prediction":[123],"consistent":[125],"with":[126,145],"longer-term":[128],"goal":[129],"durations":[132],"acoustic":[134],"features":[135],"together.":[136],"Results":[137],"indicate":[138],"proposed":[141],"method":[142],"competitive":[144],"baseline":[146],"approximating":[149],"held-out":[154],"natural":[155],"speech.":[156]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-09-16T00:00:00"}