{"id":"https://openalex.org/W2405144467","doi":"https://doi.org/10.1109/icassp.2016.7472655","title":"Robust TTS duration modelling using DNNS","display_name":"Robust TTS duration modelling using DNNS","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2405144467","doi":"https://doi.org/10.1109/icassp.2016.7472655","mag":"2405144467"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/746f6e39-8bb7-45c8-b430-42f93b971a7c","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091432739","display_name":"Gustav Eje Henter","orcid":"https://orcid.org/0000-0002-1643-1054"},"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 University of Edinburgh, Edinburgh, Edinburgh, GB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, Edinburgh, GB","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004616142","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), University of Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110238677","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), University of Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060282305","display_name":"Mirjam Wester","orcid":"https://orcid.org/0000-0002-3199-0081"},"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":"Mirjam Wester","raw_affiliation_strings":["The Centre for Speech Technology Research (CSTR), University of Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, U.K","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, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, U.K","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, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research (CSTR), University of Edinburgh, U.K","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":33,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":null,"first_page":"5130","last_page":"5134"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.773838996887207},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.6823000907897949},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6053014993667603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5289338231086731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5226407051086426},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4811033606529236},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4750280976295471},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4383043050765991},{"id":"https://openalex.org/keywords/mixture-distribution","display_name":"Mixture distribution","score":0.416317343711853},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.1879388391971588},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16932576894760132},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11497992277145386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.773838996887207},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.6823000907897949},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6053014993667603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5289338231086731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5226407051086426},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4811033606529236},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4750280976295471},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4383043050765991},{"id":"https://openalex.org/C56672385","wikidata":"https://www.wikidata.org/wiki/Q17157111","display_name":"Mixture distribution","level":3,"score":0.416317343711853},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.1879388391971588},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16932576894760132},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11497992277145386},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2016.7472655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/746f6e39-8bb7-45c8-b430-42f93b971a7c","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/746f6e39-8bb7-45c8-b430-42f93b971a7c","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":"Henter, G, Ronanki, S, Watts, O, Wester, M, Wu, Z & King, S 2016, Robust TTS Duration Modelling Using DNNs. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 5130-5134, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 20/03/16. https://doi.org/10.1109/ICASSP.2016.7472655","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/746f6e39-8bb7-45c8-b430-42f93b971a7c","is_oa":false,"landing_page_url":"http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=7472655","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":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/746f6e39-8bb7-45c8-b430-42f93b971a7c","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/746f6e39-8bb7-45c8-b430-42f93b971a7c","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":"Henter, G, Ronanki, S, Watts, O, Wester, M, Wu, Z & King, S 2016, Robust TTS Duration Modelling Using DNNs. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 5130-5134, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 20/03/16. https://doi.org/10.1109/ICASSP.2016.7472655","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/746f6e39-8bb7-45c8-b430-42f93b971a7c","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/746f6e39-8bb7-45c8-b430-42f93b971a7c","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":"Henter, G, Ronanki, S, Watts, O, Wester, M, Wu, Z & King, S 2016, Robust TTS Duration Modelling Using DNNs. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, pp. 5130-5134, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 20/03/16. https://doi.org/10.1109/ICASSP.2016.7472655","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W168261181","https://openalex.org/W1499332833","https://openalex.org/W1579853615","https://openalex.org/W1592103878","https://openalex.org/W1776535839","https://openalex.org/W1788992017","https://openalex.org/W1927421023","https://openalex.org/W1990505856","https://openalex.org/W2012712694","https://openalex.org/W2065742895","https://openalex.org/W2066452495","https://openalex.org/W2098372067","https://openalex.org/W2102003408","https://openalex.org/W2111867421","https://openalex.org/W2117890631","https://openalex.org/W2119929864","https://openalex.org/W2121044470","https://openalex.org/W2125838338","https://openalex.org/W2129142580","https://openalex.org/W2145880678","https://openalex.org/W2150612204","https://openalex.org/W2152175008","https://openalex.org/W2152205330","https://openalex.org/W2154920538","https://openalex.org/W2188827208","https://openalex.org/W2210162792","https://openalex.org/W2330005257","https://openalex.org/W2400063444","https://openalex.org/W2795431618","https://openalex.org/W2917688842","https://openalex.org/W4395958264","https://openalex.org/W6634817459","https://openalex.org/W6638144459","https://openalex.org/W6675380101","https://openalex.org/W6677973343","https://openalex.org/W6678230397","https://openalex.org/W6682825348","https://openalex.org/W6687241212","https://openalex.org/W6712610176","https://openalex.org/W6818280999","https://openalex.org/W6866122988"],"related_works":["https://openalex.org/W2348837382","https://openalex.org/W746329893","https://openalex.org/W4205872570","https://openalex.org/W4245971243","https://openalex.org/W3210882018","https://openalex.org/W2970990331","https://openalex.org/W4379116102","https://openalex.org/W3207178610","https://openalex.org/W3211782752","https://openalex.org/W4309864825"],"abstract_inverted_index":{"Accurate":[0],"modelling":[1,24,62,79],"and":[2,26,32,69,80,115],"prediction":[3,81],"of":[4,30,82,137],"speech-sound":[5],"durations":[6,84],"is":[7],"an":[8],"important":[9],"component":[10],"in":[11,97],"generating":[12],"more":[13],"natural":[14,31],"synthetic":[15,131],"speech.":[16],"Deep":[17],"neural":[18],"networks":[19,123],"(DNNs)":[20],"offer":[21],"a":[22,103,116],"powerful":[23],"paradigm,":[25],"large,":[27],"found":[28,43],"corpora":[29],"expressive":[33],"speech":[34,83,132],"are":[35,45,91],"easy":[36],"to":[37,48,59,77,93],"acquire":[38],"for":[39],"training":[40,99],"them.":[41],"Unfortunately,":[42],"datasets":[44],"seldom":[46],"subject":[47],"the":[49,98,109,140],"quality-control":[50],"that":[51,128],"traditional":[52],"synthesis":[53],"methods":[54,86],"expect.":[55],"Common":[56],"issues":[57],"likely":[58],"affect":[60],"duration":[61,138],"include":[63],"transcription":[64],"errors,":[65],"reductions,":[66],"filled":[67],"pauses,":[68],"forced-alignment":[70],"inaccuracies.":[71],"To":[72],"combat":[73],"this,":[74],"we":[75],"propose":[76],"improve":[78],"using":[85,120,134],"from":[87],"robust":[88,104,117,135],"statistics,":[89],"which":[90],"able":[92],"disregard":[94],"ill-fitting":[95],"points":[96],"material.":[100],"We":[101],"describe":[102],"fitting":[105],"criterion":[106],"based":[107],"on":[108],"density":[110,122],"power":[111],"divergence":[112],"(the":[113],"\u00df-divergence)":[114],"generation":[118],"heuristic":[119],"mixture":[121],"(MDNs).":[124],"Perceptual":[125],"tests":[126],"indicate":[127],"subjects":[129],"prefer":[130],"generated":[133],"models":[136],"over":[139],"baselines.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}