{"id":"https://openalex.org/W2921261429","doi":"https://doi.org/10.23919/apsipa.2018.8659791","title":"Speaker Adaptation for Speech Synthesis Based on Deep Neural Networks Using Hidden Semi-Markov Model Structures","display_name":"Speaker Adaptation for Speech Synthesis Based on Deep Neural Networks Using Hidden Semi-Markov Model Structures","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921261429","doi":"https://doi.org/10.23919/apsipa.2018.8659791","mag":"2921261429"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659791","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5082000911","display_name":"Kento Nakao","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kento Nakao","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067594810","display_name":"Kei Hashimoto","orcid":"https://orcid.org/0000-0003-2081-0396"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Hashimoto","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049909008","display_name":"Keiichiro Oura","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichiro Oura","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Department of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5082000911"],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19024893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":null,"first_page":"638","last_page":"643"},"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":0.9911999702453613,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9868999719619751,"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/naturalness","display_name":"Naturalness","score":0.8345133066177368},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.779178261756897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7474508881568909},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7470890879631042},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6759499311447144},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6074782609939575},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5131100416183472},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4910774230957031},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4851763844490051},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.48149216175079346},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4174532890319824},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3874852657318115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3434537649154663}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8345133066177368},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.779178261756897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474508881568909},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7470890879631042},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6759499311447144},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6074782609939575},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5131100416183472},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4910774230957031},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4851763844490051},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.48149216175079346},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4174532890319824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3874852657318115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3434537649154663},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659791","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1492383498","https://openalex.org/W1502723613","https://openalex.org/W1965255698","https://openalex.org/W1976551160","https://openalex.org/W1990505856","https://openalex.org/W1993409002","https://openalex.org/W2043003570","https://openalex.org/W2049686551","https://openalex.org/W2064218608","https://openalex.org/W2094147890","https://openalex.org/W2102003408","https://openalex.org/W2105080323","https://openalex.org/W2106792148","https://openalex.org/W2111284386","https://openalex.org/W2112021726","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2400654494","https://openalex.org/W2516321201","https://openalex.org/W2524467597","https://openalex.org/W2605320104","https://openalex.org/W4235154690","https://openalex.org/W6675380101"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2206035908","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W2535215250"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,54,85],"speaker":[4,49,90,107,116],"adaptation":[5,21,91,117],"technique":[6],"for":[7,23],"speech":[8,25,44,112],"synthesis-based":[9],"deep":[10],"neural":[11],"networks":[12],"(DNNs)":[13],"using":[14],"hidden":[15],"semi-Markov":[16],"model":[17,76],"(HSMM)":[18],"structures.":[19,95],"Speaker":[20],"techniques":[22],"DNN-based":[24],"synthesis":[26],"are":[27,45],"based":[28,118],"on":[29,119],"fixed":[30],"time-alignments":[31],"estimated":[32],"by":[33],"external":[34],"aligners.":[35],"Therefore,":[36],"the":[37,66,100,104,110,115],"acoustic":[38,79],"features":[39,80],"and":[40,88,106],"temporal":[41,94],"structures":[42],"of":[43,57,68,109],"separately":[46],"adapted":[47],"in":[48,84],"adaptation.":[50],"In":[51],"this":[52],"work,":[53],"special":[55],"type":[56],"mixture":[58],"density":[59],"network":[60],"(MDN)":[61],"called":[62],"MDN-HSMM,":[63],"which":[64],"outputs":[65],"parameters":[67],"HSMMs,":[69],"is":[70],"applied.":[71],"The":[72],"proposed":[73,101],"method":[74,102],"can":[75],"not":[77],"only":[78],"but":[81],"also":[82],"durations":[83],"unified":[86],"framework":[87],"perform":[89],"that":[92,99],"considers":[93],"Experimental":[96],"results":[97],"show":[98],"improves":[103],"naturalness":[105],"similarity":[108],"synthesized":[111],"compared":[113],"to":[114],"DNNs.":[120]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}