{"id":"https://openalex.org/W2912843901","doi":"https://doi.org/10.1109/slt.2018.8639679","title":"Examplar-Based Speechwaveform Generation for Text-To-Speech","display_name":"Examplar-Based Speechwaveform Generation for Text-To-Speech","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2912843901","doi":"https://doi.org/10.1109/slt.2018.8639679","mag":"2912843901"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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/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/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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"332","last_page":"338"},"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":0.9990000128746033,"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":0.996999979019165,"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/waveform","display_name":"Waveform","score":0.8330435752868652},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7873612642288208},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.7765179872512817},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7579474449157715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6941180229187012},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4492703974246979},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.44398176670074463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4109894335269928},{"id":"https://openalex.org/keywords/parametric-model","display_name":"Parametric model","score":0.41053149104118347},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3982670307159424},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35706406831741333},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11804282665252686},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.05859389901161194}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.8330435752868652},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7873612642288208},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.7765179872512817},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7579474449157715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6941180229187012},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4492703974246979},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.44398176670074463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4109894335269928},{"id":"https://openalex.org/C24574437","wikidata":"https://www.wikidata.org/wiki/Q7135228","display_name":"Parametric model","level":3,"score":0.41053149104118347},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3982670307159424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35706406831741333},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11804282665252686},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.05859389901161194},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2018.8639679","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639679","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/448b7f86-60df-43d2-9d8a-a66ad8856a4a","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/448b7f86-60df-43d2-9d8a-a66ad8856a4a","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":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6399999856948853,"display_name":"Peace, Justice and strong institutions"}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W176513972","https://openalex.org/W1878590289","https://openalex.org/W2024093103","https://openalex.org/W2074854222","https://openalex.org/W2123808477","https://openalex.org/W2129142580","https://openalex.org/W2170980774","https://openalex.org/W2403964578","https://openalex.org/W2406990556","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/W2777302760","https://openalex.org/W2795043217","https://openalex.org/W2888804509","https://openalex.org/W2937257593","https://openalex.org/W2949382160","https://openalex.org/W2964243274","https://openalex.org/W4231807801","https://openalex.org/W6639371816","https://openalex.org/W6713484195","https://openalex.org/W6735509194","https://openalex.org/W6761581924","https://openalex.org/W6963570432"],"related_works":["https://openalex.org/W2039489009","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1909292483","https://openalex.org/W1428730622","https://openalex.org/W1658560081","https://openalex.org/W2146616055","https://openalex.org/W596245619","https://openalex.org/W2254895521"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,9,28,37,88,102,119],"hybrid":[4],"text-to-speech":[5],"framework":[6,80],"that":[7,62,117],"uses":[8],"waveform":[10,130],"generation":[11,131],"method":[12],"based":[13],"on":[14],"examplars":[15,21],"of":[16,30,50,57,78,85,125],"natural":[17],"speech":[18,40],"waveform.":[19],"These":[20],"are":[22,67,95,108,133],"selected":[23],"at":[24],"synthesis":[25,41,53],"time":[26],"given":[27],"sequence":[29],"acoustic":[31],"features":[32],"generated":[33,68],"from":[34,69],"text":[35],"by":[36,81,97,110],"statistical":[38],"parametric":[39,72],"model.":[42,73],"In":[43],"order":[44],"to":[45],"match":[46],"the":[47,55,63,70,83,86,128,137],"expected":[48],"degradation":[49],"these":[51],"target":[52,65],"features,":[54],"database":[56],"units":[58],"is":[59],"constructed":[60],"such":[61],"units'":[64],"representations":[66],"same":[71],"We":[74,115],"evaluate":[75],"two":[76],"variants":[77,132],"this":[79],"modifying":[82],"size":[84],"examplar:":[87],"small":[89],"unit":[90,93,106],"variant":[91,104],"(where":[92,105],"boundaries":[94,107],"determined":[96,109],"pitch":[98],"mark":[99],"location)":[100],"and":[101],"halfphone":[103],"subphone":[111],"state":[112],"forced":[113],"alignment).":[114],"found":[116],"for":[118],"larger":[120],"dataset":[121],"(around":[122],"four":[123],"hours":[124],"training":[126],"data)":[127],"examplar-based":[129],"rated":[134],"higher":[135],"than":[136],"vocoder-based":[138],"system.":[139]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
