{"id":"https://openalex.org/W2406990556","doi":"https://doi.org/10.1109/icassp.2016.7472658","title":"Deep neural network-guided unit selection synthesis","display_name":"Deep neural network-guided unit selection synthesis","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2406990556","doi":"https://doi.org/10.1109/icassp.2016.7472658","mag":"2406990556"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472658","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":"article","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/A5038417409","display_name":"Thomas Merritt","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":"Thomas Merritt","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084488961","display_name":"Robert A. Clark","orcid":"https://orcid.org/0000-0002-4892-3619"},"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":"Robert A. J. Clark","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","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, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","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":["National Institute of Informatics, Japan","The Centre for Speech Technology Research, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","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, University of Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.3661,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.9855416,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5145","last_page":"5149"},"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":0.9983000159263611,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9939000010490417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7763381004333496},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7356690764427185},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7250454425811768},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.675102710723877},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6608590483665466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6036619544029236},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.576189398765564},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5525224804878235},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5071101188659668},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5017499923706055},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.47247597575187683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46068480610847473},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.421719491481781},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0968279242515564},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08581307530403137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7763381004333496},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7356690764427185},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7250454425811768},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.675102710723877},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6608590483665466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6036619544029236},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.576189398765564},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5525224804878235},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5071101188659668},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5017499923706055},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.47247597575187683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46068480610847473},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.421719491481781},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0968279242515564},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08581307530403137},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7472658","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472658","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:publications/4f504789-454c-48e1-8bae-55eb5aa793d2","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/4f504789-454c-48e1-8bae-55eb5aa793d2","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":null,"sustainable_development_goals":[],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W156280357","https://openalex.org/W192649799","https://openalex.org/W197380572","https://openalex.org/W1120805016","https://openalex.org/W1499332833","https://openalex.org/W1505932402","https://openalex.org/W1544516254","https://openalex.org/W1568585903","https://openalex.org/W1599623585","https://openalex.org/W1604596356","https://openalex.org/W1878590289","https://openalex.org/W1992287499","https://openalex.org/W2024093103","https://openalex.org/W2033178790","https://openalex.org/W2043003570","https://openalex.org/W2078597717","https://openalex.org/W2106564373","https://openalex.org/W2108048146","https://openalex.org/W2150658333","https://openalex.org/W2155433314","https://openalex.org/W2170980774","https://openalex.org/W2188827208","https://openalex.org/W2262648012","https://openalex.org/W2394761397","https://openalex.org/W2395700867","https://openalex.org/W2396931946","https://openalex.org/W2400063444","https://openalex.org/W2401318443","https://openalex.org/W2401570946","https://openalex.org/W2403132312","https://openalex.org/W2406189128","https://openalex.org/W2599840324","https://openalex.org/W2806733747","https://openalex.org/W2916535084","https://openalex.org/W2917245127","https://openalex.org/W2917688842","https://openalex.org/W4239162268","https://openalex.org/W6606352082","https://openalex.org/W6626982579","https://openalex.org/W6634213281","https://openalex.org/W6636022448","https://openalex.org/W6675901527","https://openalex.org/W6677973343","https://openalex.org/W6711832335","https://openalex.org/W6712324455","https://openalex.org/W6713281572","https://openalex.org/W6713427754","https://openalex.org/W6752004635"],"related_works":["https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W1914543332","https://openalex.org/W2387179309","https://openalex.org/W2946856121","https://openalex.org/W2388979876","https://openalex.org/W4245668640","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W2108985546"],"abstract_inverted_index":{"Vocoding":[0],"of":[1,7,18,35,43,51,53,74,106,119],"speech":[2,10,37,87],"is":[3],"a":[4],"standard":[5],"part":[6],"statistical":[8,45,66,85],"parametric":[9,29,86],"synthesis":[11,88],"systems.":[12],"It":[13],"imposes":[14],"an":[15],"upper":[16],"bound":[17],"the":[19,33,41,48,65,72,104,111,117],"naturalness":[20,52],"that":[21,71],"can":[22,39],"possibly":[23],"be":[24],"achieved.":[25],"Hybrid":[26],"systems":[27,58],"using":[28],"models":[30,46,80],"to":[31,92],"guide":[32],"selection":[34,105],"natural":[36],"units":[38,108],"combine":[40],"benefits":[42],"robust":[44],"with":[47],"high":[49],"level":[50],"waveform":[54,107],"concatenation.":[55],"Existing":[56],"hybrid":[57,93,101],"use":[59],"Hidden":[60],"Markov":[61],"Models":[62],"(HMMs)":[63],"as":[64],"model.":[67],"This":[68],"paper":[69],"demonstrates":[70],"superiority":[73],"Deep":[75],"Neural":[76],"Network":[77],"(DNN)":[78],"acoustic":[79],"over":[81,91],"HMMs":[82],"in":[83,109,116],"conventional":[84],"also":[89],"carries":[90],"synthesis.":[94],"We":[95],"compare":[96],"various":[97],"DNN":[98],"and":[99],"HMM":[100],"configurations,":[102],"guiding":[103],"either":[110],"vocoder":[112],"parameter":[113],"domain,":[114],"or":[115],"domain":[118],"embeddings":[120],"(bottleneck":[121],"features).":[122]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
