{"id":"https://openalex.org/W3008540909","doi":"https://doi.org/10.1145/3372244","title":"Learning and Modeling Unit Embeddings Using Deep Neural Networks for Unit-Selection-Based Mandarin Speech Synthesis","display_name":"Learning and Modeling Unit Embeddings Using Deep Neural Networks for Unit-Selection-Based Mandarin Speech Synthesis","publication_year":2020,"publication_date":"2020-01-09","ids":{"openalex":"https://openalex.org/W3008540909","doi":"https://doi.org/10.1145/3372244","mag":"3008540909"},"language":"en","primary_location":{"id":"doi:10.1145/3372244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372244","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-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/A5084534688","display_name":"Zhou Xiao","orcid":"https://orcid.org/0000-0001-5263-365X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Zhou","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3911,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67332399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"19","issue":"3","first_page":"1","last_page":"14"},"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":0.9966999888420105,"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/computer-science","display_name":"Computer science","score":0.7355780005455017},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.643418550491333},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6063801050186157},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5547423362731934},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5492187142372131},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5078378319740295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4734606146812439},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.45725104212760925},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44474610686302185},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.42859840393066406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15994107723236084},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08706316351890564}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355780005455017},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.643418550491333},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6063801050186157},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5547423362731934},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5492187142372131},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5078378319740295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4734606146812439},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.45725104212760925},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44474610686302185},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.42859840393066406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15994107723236084},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08706316351890564},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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:10.1145/3372244","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3372244","pdf_url":null,"source":{"id":"https://openalex.org/S4306421405","display_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","issn_l":"2375-4699","issn":["2375-4699","2375-4702"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian and Low-Resource Language Information Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4961818081","display_name":null,"funder_award_id":"61871358, U1636201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1499332833","https://openalex.org/W1600722501","https://openalex.org/W1963627370","https://openalex.org/W1973766695","https://openalex.org/W2019447133","https://openalex.org/W2024093103","https://openalex.org/W2043003570","https://openalex.org/W2049686551","https://openalex.org/W2128160875","https://openalex.org/W2129142580","https://openalex.org/W2154920538","https://openalex.org/W2187089797","https://openalex.org/W2406990556","https://openalex.org/W2558906580","https://openalex.org/W2674088828","https://openalex.org/W2746788734","https://openalex.org/W2749651610","https://openalex.org/W2774933427","https://openalex.org/W2792191066","https://openalex.org/W2883746099","https://openalex.org/W2888976811","https://openalex.org/W2964243274","https://openalex.org/W2997437965","https://openalex.org/W4253506752"],"related_works":["https://openalex.org/W234770729","https://openalex.org/W2588431733","https://openalex.org/W2391796527","https://openalex.org/W2387179309","https://openalex.org/W2388979876","https://openalex.org/W4245668640","https://openalex.org/W2032960563","https://openalex.org/W2142993035","https://openalex.org/W2899044948","https://openalex.org/W15468680"],"abstract_inverted_index":{"A":[0],"method":[1],"of":[2,47,77,101,146,152,159,191,198,221],"learning":[3,106,213,235],"and":[4,98,124,127,179,195,214],"modeling":[5,215],"unit":[6,25,37,79,102,121,150,172,184,216,226,236],"embeddings":[7,217,237],"using":[8,242],"deep":[9],"neutral":[10],"networks":[11],"(DNNs)":[12],"is":[13,27,70,108],"presented":[14],"in":[15,39,60,81],"this":[16],"article":[17],"for":[18,34,110,234],"unit-selection-based":[19],"Mandarin":[20,207],"speech":[21,208,228],"synthesis.":[22,229],"Here,":[23],"a":[24,30,35,40,64,104,189,196,206],"embedding":[26,32,44,68,75,92,143],"defined":[28],"as":[29,162,188],"fixed-length":[31],"vector":[33],"phone-sized":[36,43],"candidate":[38],"corpus.":[41],"Modeling":[42],"vectors":[45,76,93,151,173],"instead":[46],"frame-sized":[48],"acoustic":[49,97,119,244],"features":[50,139,158],"can":[51],"better":[52,239],"measure":[53],"the":[54,74,82,90,111,141,149,156,168,171,180,192,199,219],"long-term":[55],"dependencies":[56],"among":[57],"consecutive":[58],"units":[59],"an":[61,67],"utterance.":[62],"First,":[63],"DNN":[65],"with":[66],"layer":[69],"built":[71],"to":[72,88,94,136,247],"learn":[73],"all":[78],"candidates":[80,185],"corpus":[83,210],"from":[84,183],"scratch.":[85],"In":[86],"order":[87],"enable":[89],"extracted":[91,142],"carry":[95],"both":[96],"linguistic":[99,138,157],"information":[100],"candidates,":[103],"multitarget":[105],"strategy":[107],"designed":[109],"DNN.":[112],"Its":[113],"optional":[114],"prediction":[115],"targets":[116,233,245],"include":[117],"frame-level":[118],"features,":[120],"durations,":[122],"monophone":[123],"tone":[125],"identifiers,":[126],"context":[128],"classes.":[129],"Then,":[130],"another":[131],"two":[132,177],"DNNs":[133,178],"are":[134,186],"constructed":[135],"map":[137],"toward":[140],"vectors.":[144],"One":[145],"them":[147],"employs":[148],"preceding":[153],"phones":[154],"besides":[155],"current":[160],"phone":[161],"its":[163],"input.":[164],"At":[165],"synthesis":[166,209],"time,":[167],"distances":[169],"between":[170],"predicted":[174],"by":[175],"these":[176],"ones":[181],"derived":[182],"used":[187],"part":[190,197],"target":[193],"cost":[194],"concatenation":[200],"cost,":[201],"respectively.":[202],"Our":[203],"experiments":[204],"on":[205],"demonstrate":[211],"that":[212],"improve":[218],"naturalness":[220],"hidden":[222],"Markov":[223],"model":[224],"(HMM)-based":[225],"selection":[227],"Furthermore,":[230],"integrating":[231],"multiple":[232],"achieves":[238],"performance":[240],"than":[241],"only":[243],"according":[246],"our":[248],"subjective":[249],"evaluation":[250],"results.":[251]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}