{"id":"https://openalex.org/W2513112113","doi":"https://doi.org/10.21437/ssw.2016-17","title":"Parallel and cascaded deep neural networks for text-to-speech synthesis","display_name":"Parallel and cascaded deep neural networks for text-to-speech synthesis","publication_year":2016,"publication_date":"2016-09-13","ids":{"openalex":"https://openalex.org/W2513112113","doi":"https://doi.org/10.21437/ssw.2016-17","mag":"2513112113"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2016-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)","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/A5109494794","display_name":"Manuel Sam Ribeiro","orcid":"https://orcid.org/0000-0001-8096-2231"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Manuel Sam Ribeiro","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110238677","display_name":"Oliver Watts","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliver Watts","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["School of Informatics"],"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109494794"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7139,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.89073654,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"100","last_page":"105"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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/T10028","display_name":"Topic Modeling","score":0.9965999722480774,"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":0.721143364906311},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5495256185531616},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5309253334999084},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5176551938056946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43906140327453613},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.397884726524353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.721143364906311},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5495256185531616},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5309253334999084},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5176551938056946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43906140327453613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.397884726524353}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/ssw.2016-17","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2016-17","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"9th ISCA Workshop on Speech Synthesis Workshop (SSW 9)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/97eb752a-897a-4065-a85b-3cb3135dcd22","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/parallel-and-cascaded-deep-neural-networks-for-texttospeech-synthesis(97eb752a-897a-4065-a85b-3cb3135dcd22).html","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/4","score":0.47999998927116394,"display_name":"Quality Education"}],"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/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"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":30,"referenced_works":["https://openalex.org/W36638734","https://openalex.org/W113106864","https://openalex.org/W251642908","https://openalex.org/W397522103","https://openalex.org/W1499332833","https://openalex.org/W1517939602","https://openalex.org/W1540083112","https://openalex.org/W1571950845","https://openalex.org/W1578102511","https://openalex.org/W1614298861","https://openalex.org/W1977362129","https://openalex.org/W2029190953","https://openalex.org/W2029434926","https://openalex.org/W2078597717","https://openalex.org/W2102003408","https://openalex.org/W2106564373","https://openalex.org/W2109938215","https://openalex.org/W2111284386","https://openalex.org/W2123345066","https://openalex.org/W2127589467","https://openalex.org/W2139525902","https://openalex.org/W2153579005","https://openalex.org/W2158504378","https://openalex.org/W2184310502","https://openalex.org/W2291915740","https://openalex.org/W2296111744","https://openalex.org/W2394662942","https://openalex.org/W2402019113","https://openalex.org/W2517736208","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2216757598","https://openalex.org/W2391251536","https://openalex.org/W234770729","https://openalex.org/W2362198218","https://openalex.org/W1982750869","https://openalex.org/W2019521278","https://openalex.org/W1984922432","https://openalex.org/W4387496629","https://openalex.org/W3013209356","https://openalex.org/W3204019825"],"abstract_inverted_index":{"An":[0],"investigation":[1],"of":[2,33,40,99],"cascaded":[3,58,64,127],"and":[4,20,29,80,86],"parallel":[5,61,77,122],"deep":[6],"neural":[7],"networks":[8,35,123],"for":[9],"speech":[10],"synthesis":[11],"is":[12,109],"conducted.In":[13],"these":[14],"systems,":[15],"suprasegmental":[16,31,66,81],"linguistic":[17,42,101],"features":[18,27,82,102],"(syllable-level":[19],"above)":[21],"are":[22,49,68,83,93,114,124],"processed":[23,84],"separately":[24,85],"from":[25],"segmental":[26,46,79],"(phone-level":[28],"below).The":[30],"component":[32],"the":[34,63,73,76,118],"learns":[36],"compact":[37],"distributed":[38],"representations":[39,48,67],"high-level":[41],"units":[43],"without":[44],"any":[45],"influence.These":[47],"then":[50],"integrated":[51],"into":[52],"a":[53,57,60,89,96,106],"frame-level":[54],"system":[55],"using":[56],"or":[59],"approach.In":[62],"network,":[65,78],"used":[69],"as":[70,103,105],"input":[71],"to":[72],"framelevel":[74],"network.In":[75],"concatenated":[87],"at":[88],"later":[90],"stage.These":[91],"experiments":[92],"conducted":[94],"with":[95],"standard":[97],"set":[98],"high-dimensional":[100],"well":[104],"hand-pruned":[107],"one.It":[108],"observed":[110],"that":[111],"hierarchical":[112],"systems":[113],"consistently":[115],"preferred":[116,125],"over":[117,126],"baseline":[119],"feedforward":[120],"systems.Similarly,":[121],"networks.":[128]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}