{"id":"https://openalex.org/W2912613132","doi":"https://doi.org/10.1109/slt.2018.8639588","title":"Hierarchical RNNs for Waveform-Level Speech Synthesis","display_name":"Hierarchical RNNs for Waveform-Level Speech Synthesis","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2912613132","doi":"https://doi.org/10.1109/slt.2018.8639588","mag":"2912613132"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639588","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":"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/A5033136699","display_name":"Qingyun Dou","orcid":"https://orcid.org/0000-0001-8479-7210"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Qingyun Dou","raw_affiliation_strings":["Cambridge University Engineering Department, UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037274400","display_name":"Moquan Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Moquan Wan","raw_affiliation_strings":["Cambridge University Engineering Department, UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028787670","display_name":"Gilles Degottex","orcid":"https://orcid.org/0000-0003-1346-9919"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gilles Degottex","raw_affiliation_strings":["Cambridge University Engineering Department, UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101110036","display_name":"Zhiyi Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhiyi Ma","raw_affiliation_strings":["Cambridge University Engineering Department, UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark J.F. Gales","raw_affiliation_strings":["Cambridge University Engineering Department, UK"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033136699"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.3384,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7084656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"618","last_page":"625"},"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":0.998199999332428,"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":0.9959999918937683,"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/speech-synthesis","display_name":"Speech synthesis","score":0.8215723037719727},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.816270112991333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.674679160118103},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6474536657333374},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6348133087158203},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5375105738639832},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.48861104249954224},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.46489280462265015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38461190462112427},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06631073355674744}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8215723037719727},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.816270112991333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.674679160118103},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6474536657333374},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6348133087158203},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5375105738639832},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.48861104249954224},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.46489280462265015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38461190462112427},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06631073355674744},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2018.8639588","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639588","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:generic.eprints.org:1078249","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/1078249/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1677182931","https://openalex.org/W1810943226","https://openalex.org/W1815076433","https://openalex.org/W1924770834","https://openalex.org/W1964420823","https://openalex.org/W2025638820","https://openalex.org/W2043003570","https://openalex.org/W2045158511","https://openalex.org/W2064675550","https://openalex.org/W2097039814","https://openalex.org/W2102003408","https://openalex.org/W2129142580","https://openalex.org/W2150658333","https://openalex.org/W2273818272","https://openalex.org/W2284050935","https://openalex.org/W2285182995","https://openalex.org/W2337335398","https://openalex.org/W2394761397","https://openalex.org/W2428180336","https://openalex.org/W2519091744","https://openalex.org/W2524251915","https://openalex.org/W2584032004","https://openalex.org/W2750938222","https://openalex.org/W2803229097","https://openalex.org/W2901997113","https://openalex.org/W2952276042","https://openalex.org/W2953318193","https://openalex.org/W2963685250","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W3106271744","https://openalex.org/W4298580827","https://openalex.org/W4395958148","https://openalex.org/W6631190155","https://openalex.org/W6638273328","https://openalex.org/W6638545294","https://openalex.org/W6640212811","https://openalex.org/W6674500526","https://openalex.org/W6675380101","https://openalex.org/W6680587008","https://openalex.org/W6695676441","https://openalex.org/W6696079272","https://openalex.org/W6732429163","https://openalex.org/W6746700228","https://openalex.org/W6748409065","https://openalex.org/W6756197946","https://openalex.org/W6865592293"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2351992668","https://openalex.org/W2324828474","https://openalex.org/W2374315191","https://openalex.org/W2391207559","https://openalex.org/W2039489009","https://openalex.org/W3115948027","https://openalex.org/W2405110677","https://openalex.org/W4387323809","https://openalex.org/W2811496854"],"abstract_inverted_index":{"Speech":[0],"synthesis":[1,17,30,36,72,121],"technology":[2],"has":[3],"a":[4,70,112,150,162,174],"wide":[5],"range":[6,33],"of":[7,28,34,46,58,118,140,183],"applications":[8],"such":[9],"as":[10,23,133],"voice":[11,172],"assistants.":[12],"In":[13],"recent":[14],"years":[15],"waveform-level":[16,35],"systems":[18,37],"have":[19,38],"achieved":[20],"state-of-the-art":[21],"performance,":[22],"they":[24],"overcome":[25],"the":[26,44,56,103,158],"limitations":[27],"vocoder-based":[29,71],"systems.":[31],"A":[32],"been":[39],"proposed;":[40],"this":[41,109,128],"paper":[42,110],"investigates":[43],"performance":[45,95],"hierarchical":[47,104],"Recurrent":[48],"Neural":[49],"Networks":[50],"(RNNs)":[51],"for":[52,185],"speech":[53],"synthesis.":[54],"First,":[55],"form":[57],"network":[59],"conditioning":[60,82,102],"is":[61,75,98,116,124,131],"discussed,":[62],"comparing":[63],"linguistic":[64,80],"features":[65,68,85,142],"and":[66,89,92,166],"vocoder":[67,84,107,130,141,160],"from":[69],"system.":[73],"It":[74],"found":[76],"that":[77,157,167],"compared":[78],"with":[79],"features,":[81,108],"on":[83,106],"requires":[86],"less":[87,179],"data":[88,184],"modeling":[90],"power,":[91],"yields":[93],"better":[94],"when":[96,122],"there":[97,123],"limited":[99],"data.":[100,126],"By":[101],"RNN":[105],"develops":[111],"neural":[113,129,159],"vocoder,":[114],"which":[115],"capable":[117],"high":[119,163],"quality":[120,164],"sufficient":[125],"Furthermore,":[127],"flexible,":[132],"conceptually":[134],"it":[135,168],"can":[136,169],"map":[137],"any":[138],"sequence":[139],"to":[143,149,173],"speech,":[144],"enabling":[145],"efficient":[146],"synthesizer":[147],"porting":[148],"target":[151],"speaker.":[152],"Subjective":[153],"listening":[154],"tests":[155],"demonstrate":[156],"outperforms":[161],"baseline,":[165],"change":[170],"its":[171],"very":[175],"different":[176],"speaker,":[177],"given":[178],"than":[180],"15":[181],"minutes":[182],"fine":[186],"tuning.":[187]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}