{"id":"https://openalex.org/W1982347857","doi":"https://doi.org/10.1109/chinasip.2013.6625315","title":"Multi-speaker prosodic instance selection for HMM-based speech synthesis","display_name":"Multi-speaker prosodic instance selection for HMM-based speech synthesis","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W1982347857","doi":"https://doi.org/10.1109/chinasip.2013.6625315","mag":"1982347857"},"language":"en","primary_location":{"id":"doi:10.1109/chinasip.2013.6625315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/chinasip.2013.6625315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE China Summit and International Conference on Signal and Information Processing","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/A5020291213","display_name":"Yansuo Yu","orcid":"https://orcid.org/0000-0002-2603-7755"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yansuo Yu","raw_affiliation_strings":["Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), School of Electronics Engineering and Computer Science, Peking University, Beijing, China","Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), School of Electronics Engineering and Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078334710","display_name":"Fengyun Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengyun Zhu","raw_affiliation_strings":["Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), School of Electronics Engineering and Computer Science, Peking University, Beijing, China","Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), School of Electronics Engineering and Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), School of Electronics Engineering and Computer Science, Peking University, Beijing, China","Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), School of Electronics Engineering and Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab. of Machine Perception (Minist. of Educ.), Peking Univ., Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020291213"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06025809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":null,"first_page":"142","last_page":"146"},"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":0.9980999827384949,"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":0.991599977016449,"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":0.7614707946777344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.758455753326416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7145926356315613},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.6663873791694641},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6265504360198975},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6142482757568359},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5662127137184143},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5402774810791016},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5210192203521729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41565030813217163},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07467225193977356}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7614707946777344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.758455753326416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7145926356315613},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.6663873791694641},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6265504360198975},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6142482757568359},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5662127137184143},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5402774810791016},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5210192203521729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41565030813217163},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07467225193977356},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/chinasip.2013.6625315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/chinasip.2013.6625315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE China Summit and International Conference on Signal and Information Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W14365481","https://openalex.org/W59470279","https://openalex.org/W1600722501","https://openalex.org/W1973766695","https://openalex.org/W1992287499","https://openalex.org/W2049686551","https://openalex.org/W2109938215","https://openalex.org/W2147868561","https://openalex.org/W2149244738","https://openalex.org/W2150658333","https://openalex.org/W2166823384","https://openalex.org/W2376932199","https://openalex.org/W7056901721","https://openalex.org/W7075637324"],"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":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5],"novel":[6],"parametric":[7,124],"speech":[8,21],"synthesis":[9,125],"based":[10],"on":[11,108],"prosodic":[12,47,60,66,88,96],"instance":[13],"selection":[14],"to":[15,44,74,83],"improve":[16],"the":[17,24,42,53,87,93,99,109,115],"naturalness":[18],"of":[19,26,78,95,104],"synthesized":[20,100],"especially":[22],"in":[23],"case":[25],"small":[27],"database.":[28],"Prosodic":[29],"instances":[30,67],"including":[31],"F":[32],"<sub":[33],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[34],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</sub>":[35],"and":[36,59,126],"duration":[37],"are":[38,72,81],"directly":[39],"selected":[40],"from":[41,52,68],"database":[43],"preserve":[45],"rich":[46],"variations":[48],"other":[49],"than":[50,76,122],"generation":[51],"statistical":[54],"models.":[55],"Considering":[56],"that":[57,114],"spectral":[58],"parameters":[61],"could":[62],"be":[63],"modeled":[64],"separately,":[65],"multiple":[69],"speakers,":[70],"which":[71],"easier":[73],"obtain":[75],"those":[77],"single":[79],"speaker,":[80],"exploited":[82],"not":[84],"only":[85],"enhance":[86],"models":[89],"but":[90],"also":[91],"enrich":[92],"coverage":[94],"context":[97],"for":[98],"speaker.":[101],"The":[102],"results":[103],"subjective":[105],"listening":[106],"tests":[107],"corresponding":[110],"databases":[111],"further":[112],"show":[113],"proposed":[116],"method":[117],"can":[118],"achieve":[119],"better":[120],"performance":[121],"both":[123],"waveform":[127],"concatenation":[128],"synthesis.":[129]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}