{"id":"https://openalex.org/W2888804509","doi":"https://doi.org/10.21437/interspeech.2018-1857","title":"Exemplar-based Speech Waveform Generation","display_name":"Exemplar-based Speech Waveform Generation","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2888804509","doi":"https://doi.org/10.21437/interspeech.2018-1857","mag":"2888804509"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1857","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/ba53177b-cef1-4a38-b5ed-28c293e30333","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[{"id":"https://openalex.org/I185658715","display_name":"Universities UK","ror":"https://ror.org/00mmfs450","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I185658715"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["The Centre for Speech Technology Research, Edinburgh University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, Edinburgh University, UK","institution_ids":["https://openalex.org/I185658715"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019012876","display_name":"Cassia Valentini-Botinhao","orcid":"https://orcid.org/0000-0002-3486-8620"},"institutions":[{"id":"https://openalex.org/I185658715","display_name":"Universities UK","ror":"https://ror.org/00mmfs450","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I185658715"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cassia Valentini-Botinhao","raw_affiliation_strings":["The Centre for Speech Technology Research, Edinburgh University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, Edinburgh University, UK","institution_ids":["https://openalex.org/I185658715"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015826496","display_name":"Felipe Espic","orcid":null},"institutions":[{"id":"https://openalex.org/I185658715","display_name":"Universities UK","ror":"https://ror.org/00mmfs450","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I185658715"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Felipe Espic","raw_affiliation_strings":["The Centre for Speech Technology Research, Edinburgh University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, Edinburgh University, UK","institution_ids":["https://openalex.org/I185658715"]}]},{"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/I185658715","display_name":"Universities UK","ror":"https://ror.org/00mmfs450","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I185658715"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research, Edinburgh University, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, Edinburgh University, UK","institution_ids":["https://openalex.org/I185658715"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185658715"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2022","last_page":"2026"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9984999895095825,"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":0.9983000159263611,"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":0.8523697853088379},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7858679294586182},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5763389468193054},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4936552941799164},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4796912372112274},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.45995795726776123},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.45390430092811584},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43827024102211},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.42159369587898254},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3936087489128113},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13455712795257568},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.12246838212013245}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8523697853088379},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7858679294586182},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5763389468193054},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4936552941799164},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4796912372112274},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.45995795726776123},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.45390430092811584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43827024102211},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.42159369587898254},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3936087489128113},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13455712795257568},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.12246838212013245},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2018-1857","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/ba53177b-cef1-4a38-b5ed-28c293e30333","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/ba53177b-cef1-4a38-b5ed-28c293e30333","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":"Watts, O, Valentini Botinhao, C, Espic calder\u00f3n, F & King, S 2018, Exemplar-based Speech Waveform Generation. in Interspeech 2018. Hyderabad, India, pp. 2022-2026, Interspeech 2018, Hyderabad, India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-1857","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/ba53177b-cef1-4a38-b5ed-28c293e30333","is_oa":false,"landing_page_url":"https://www.isca-speech.org/archive/Interspeech_2018/pdfs/1857.pdf","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/ba53177b-cef1-4a38-b5ed-28c293e30333","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/ba53177b-cef1-4a38-b5ed-28c293e30333","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":"Watts, O, Valentini Botinhao, C, Espic calder\u00f3n, F & King, S 2018, Exemplar-based Speech Waveform Generation. in Interspeech 2018. Hyderabad, India, pp. 2022-2026, Interspeech 2018, Hyderabad, India, 2/09/18. https://doi.org/10.21437/Interspeech.2018-1857","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7898478334","display_name":null,"funder_award_id":"EP/P011586/1","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":18,"referenced_works":["https://openalex.org/W176513972","https://openalex.org/W1544516254","https://openalex.org/W2024093103","https://openalex.org/W2123808477","https://openalex.org/W2129142580","https://openalex.org/W2170980774","https://openalex.org/W2403964578","https://openalex.org/W2406990556","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2598638573","https://openalex.org/W2613407020","https://openalex.org/W2674088828","https://openalex.org/W2747681982","https://openalex.org/W2749609415","https://openalex.org/W2749651610","https://openalex.org/W2964243274"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W2176409448","https://openalex.org/W3040712279"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,21,30,37,107,145],"simple":[4],"but":[5,115],"effective":[6],"method":[7,26,129],"for":[8,33,56,61,66,150],"generating":[9],"speech":[10,18],"waveforms":[11],"by":[12,85],"selecting":[13],"small":[14],"units":[15],"of":[16,109],"stored":[17],"to":[19,125],"match":[20],"low-dimensional":[22],"target":[23,63,97,110],"representation.":[24],"The":[25,128],"is":[27,130],"designed":[28],"as":[29],"drop-in":[31],"replacement":[32],"the":[34,135],"vocoder":[35],"in":[36,102],"deep":[38],"neural":[39],"network-based":[40],"text-to-speech":[41],"system.":[42],"Most":[43],"previous":[44],"work":[45],"on":[46,53],"hybrid":[47],"unit":[48,58,103],"selection":[49],"waveform":[50,72,136],"generation":[51],"relies":[52],"phonetic":[54,76],"annotation":[55],"determining":[57],"<br/>boundaries,":[59],"or":[60,65,79],"specifying":[62],"cost,":[64,114],"candidate":[67],"preselection.":[68],"In":[69],"contrast,":[70],"our":[71,152],"generator":[73],"requires":[74],"no":[75],"information,":[77],"annotation,":[78],"alignment.":[80],"Unit":[81],"boundaries":[82],"are":[83,93],"determined":[84],"epochs,":[86],"and":[87,112,132,143],"spectral":[88],"analysis":[89],"provides":[90],"representations":[91],"which":[92],"compared":[94],"directly":[95],"with":[96],"features":[98],"at":[99],"runtime.":[100],"As":[101],"selection,":[104],"we":[105],"minimise":[106],"combination":[108],"cost":[111],"join":[113],"find":[116],"that":[117],"greedy":[118],"left-to-right":[119],"nearest-neighbour":[120],"search":[121],"gives":[122],"similar":[123],"results":[124],"dynamic":[126],"programming.":[127],"fast":[131],"can":[133],"generate":[134],"incrementally.":[137],"We":[138],"use":[139],"publicly":[140],"available":[141],"data":[142],"provide":[144],"permissively-licensed":[146],"open":[147],"source":[148],"toolkit":[149],"reproducing":[151],"results.":[153]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}