{"id":"https://openalex.org/W2890606114","doi":"https://doi.org/10.1109/icassp.2018.8461888","title":"Adaptation of an Expressive Single Speaker Deep Neural Network Speech Synthesis System","display_name":"Adaptation of an Expressive Single Speaker Deep Neural Network Speech Synthesis System","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2890606114","doi":"https://doi.org/10.1109/icassp.2018.8461888","mag":"2890606114"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5003499948","display_name":"Jonathan Parker","orcid":"https://orcid.org/0000-0001-7563-1630"},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonathan Parker","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035745788","display_name":"Yannis Stylianou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yannis Stylianou","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018207993","display_name":"Roberto Cipolla","orcid":"https://orcid.org/0000-0002-8999-2151"},"institutions":[{"id":"https://openalex.org/I4210143477","display_name":"Toshiba (United Kingdom)","ror":"https://ror.org/054hmd463","country_code":"GB","type":"company","lineage":["https://openalex.org/I1292669757","https://openalex.org/I4210143477"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Roberto Cipolla","raw_affiliation_strings":["Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toshiba Research Europe Limited, Cambridge Research Laboratory, Cambridge, UK","institution_ids":["https://openalex.org/I4210143477"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1827,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84537178,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"21","issue":null,"first_page":"5309","last_page":"5313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9876999855041504,"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":0.982699990272522,"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-recognition","display_name":"Speech recognition","score":0.8174540996551514},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7151046991348267},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6109039783477783},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6067724227905273},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5741569399833679},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5717432498931885},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5077725052833557},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4493657350540161},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44047677516937256},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4243719279766083},{"id":"https://openalex.org/keywords/expression","display_name":"Expression (computer science)","score":0.41179561614990234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35320836305618286},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07839009165763855},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06706497073173523}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8174540996551514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7151046991348267},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6109039783477783},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6067724227905273},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5741569399833679},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5717432498931885},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5077725052833557},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4493657350540161},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44047677516937256},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4243719279766083},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.41179561614990234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35320836305618286},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07839009165763855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06706497073173523},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2018.8461888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:1034013","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/1034013/","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":11,"referenced_works":["https://openalex.org/W1971670143","https://openalex.org/W2020024436","https://openalex.org/W2045158511","https://openalex.org/W2102003408","https://openalex.org/W2394882406","https://openalex.org/W2494654097","https://openalex.org/W2562274522","https://openalex.org/W2605320104","https://openalex.org/W2721682741","https://openalex.org/W2746498480","https://openalex.org/W2759925408"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"One":[0],"of":[1,4,15,18],"the":[2,10,16,19,23,59,66,91],"advantages":[3],"statistical":[5],"parametric":[6],"speech":[7,20,44,57,93],"synthesis":[8,45],"is":[9],"ability":[11],"to":[12,34,47],"alter":[13],"some":[14],"characteristics":[17],"e.g.":[21],"change":[22],"speaker,":[24,50],"expression":[25,87],"etc.":[26],"In":[27],"this":[28],"paper":[29],"we":[30],"present":[31],"a":[32,48],"technique":[33,69],"adapt":[35],"an":[36],"expressive":[37,56,78,92],"single":[38],"speaker":[39,82,99],"deep":[40],"neural":[41],"network":[42],"(DNN)":[43],"model":[46],"new":[49,60],"allowing":[51],"for":[52],"both":[53,75],"neutral":[54,76],"and":[55,77,80,84],"in":[58],"speaker's":[61],"voice.":[62],"Experiments":[63],"show":[64],"that":[65],"proposed":[67],"adaptation":[68,100],"achieves":[70],"higher":[71,81],"MOS":[72],"scores":[73,89],"on":[74,90],"speech,":[79],"similarity":[83,88],"slightly":[85],"lower":[86],"when":[94],"compared":[95],"with":[96],"another":[97],"DNN":[98],"technique.":[101]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}