{"id":"https://openalex.org/W2922185715","doi":"https://doi.org/10.23919/apsipa.2018.8659668","title":"A DNN-based Mandarin-Tibetan cross-lingual speech synthesis","display_name":"A DNN-based Mandarin-Tibetan cross-lingual speech synthesis","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2922185715","doi":"https://doi.org/10.23919/apsipa.2018.8659668","mag":"2922185715"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659668","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659668","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/A5101399960","display_name":"Weitong Guo","orcid":"https://orcid.org/0009-0004-1664-1424"},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weitong Guo","raw_affiliation_strings":["College of Physics and Electronica Engineering, Northwest Normal University, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Electronica Engineering, Northwest Normal University, Lanzhou, China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032919424","display_name":"Hongwu Yang","orcid":"https://orcid.org/0000-0002-8939-3386"},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwu Yang","raw_affiliation_strings":["College of Physics and Electronica Engineering, Northwest Normal University, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Electronica Engineering, Northwest Normal University, Lanzhou, China","institution_ids":["https://openalex.org/I68986083"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012172321","display_name":"Zhenye Gan","orcid":"https://orcid.org/0000-0003-1477-4958"},"institutions":[{"id":"https://openalex.org/I68986083","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908","country_code":"CN","type":"education","lineage":["https://openalex.org/I68986083"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenye Gan","raw_affiliation_strings":["College of Physics and Electronica Engineering, Northwest Normal University, Lanzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Physics and Electronica Engineering, Northwest Normal University, Lanzhou, China","institution_ids":["https://openalex.org/I68986083"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101399960"],"corresponding_institution_ids":["https://openalex.org/I68986083"],"apc_list":null,"apc_paid":null,"fwci":1.0142,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83462972,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1702","last_page":"1707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9873999953269958,"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/T11309","display_name":"Music and Audio Processing","score":0.9704999923706055,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.9164004921913147},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7640844583511353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7402070164680481},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7263461351394653},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5986108183860779},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5677416324615479},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5299193859100342},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5174577832221985},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4237551689147949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3983609676361084},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13937675952911377},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09809818863868713}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.9164004921913147},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7640844583511353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402070164680481},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7263461351394653},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5986108183860779},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5677416324615479},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5299193859100342},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5174577832221985},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4237551689147949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3983609676361084},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13937675952911377},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09809818863868713},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.23919/apsipa.2018.8659668","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659668","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"},{"id":"pmh:oai:ir.lzu.edu.cn/:262010/282171","is_oa":false,"landing_page_url":"http://ir.lzu.edu.cn/handle/262010/282171","pdf_url":null,"source":{"id":"https://openalex.org/S4406923049","display_name":"Lanzhou University Institutional Repository","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":"Proceedings Paper"},{"id":"pmh:oai:ir.lzu.edu.cn/:262010/403990","is_oa":false,"landing_page_url":"http://ir.lzu.edu.cn/handle/262010/403990","pdf_url":null,"source":{"id":"https://openalex.org/S4406923049","display_name":"Lanzhou University Institutional Repository","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 article (CA)"},{"id":"pmh:oai:ir.lzu.edu.cn/:262010/269658","is_oa":false,"landing_page_url":"http://ir.lzu.edu.cn/handle/262010/269658","pdf_url":null,"source":{"id":"https://openalex.org/S4406923049","display_name":"Lanzhou University Institutional Repository","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":"\u4f1a\u8bae\u8bba\u6587"},{"id":"pmh:oai:ir.lzu.edu.cn/:262010/281363","is_oa":false,"landing_page_url":"http://ir.lzu.edu.cn/handle/262010/281363","pdf_url":null,"source":{"id":"https://openalex.org/S4406923049","display_name":"Lanzhou University Institutional Repository","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":"Proceedings Paper"},{"id":"pmh:oai:ir.lzu.edu.cn/:262010/293280","is_oa":false,"landing_page_url":"http://ir.lzu.edu.cn/handle/262010/293280","pdf_url":null,"source":{"id":"https://openalex.org/S4406923049","display_name":"Lanzhou University Institutional Repository","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":"Proceedings Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320312274","display_name":"Northwest Normal University","ror":"https://ror.org/00gx3j908"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322439","display_name":"Northwest University","ror":"https://ror.org/00z3td547"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W40001856","https://openalex.org/W113498433","https://openalex.org/W202820833","https://openalex.org/W349236604","https://openalex.org/W1499332833","https://openalex.org/W1570874634","https://openalex.org/W1570923747","https://openalex.org/W1571950845","https://openalex.org/W1572989473","https://openalex.org/W1602430027","https://openalex.org/W1968026859","https://openalex.org/W1990560471","https://openalex.org/W2014869452","https://openalex.org/W2076638338","https://openalex.org/W2081254602","https://openalex.org/W2102003408","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2136229648","https://openalex.org/W2150341604","https://openalex.org/W2150769028","https://openalex.org/W2370384815","https://openalex.org/W2400136144","https://openalex.org/W2574456902","https://openalex.org/W2605320104","https://openalex.org/W4205947740","https://openalex.org/W6601627100","https://openalex.org/W6608260493","https://openalex.org/W6634201745","https://openalex.org/W6636404455","https://openalex.org/W6712527251","https://openalex.org/W6736204136","https://openalex.org/W7052914440"],"related_works":["https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W2152945827","https://openalex.org/W114226241","https://openalex.org/W2015513221","https://openalex.org/W301864623"],"abstract_inverted_index":{"The":[0,17,57,77],"paper":[1],"proposed":[2,106,149],"a":[3,36,46,52,64],"deep":[4],"neural":[5],"network":[6],"(DNN)-based":[7],"Mandarin-Tibetan":[8],"cross-lingual":[9],"speech":[10,26,79,82,103,126,136,156,163],"synthesis":[11,27,127,157],"by":[12,86,104],"adopting":[13],"speaker":[14,58],"adaptation":[15],"training.":[16],"initial":[18],"and":[19,32,51,96],"the":[20,25,105,113,123,141,148,155],"final":[21],"are":[22,108],"used":[23],"as":[24],"units":[28],"for":[29],"both":[30],"Mandarin":[31,48,71,78,145],"Tibetan":[33,54,73,81,102,125,130,134],"to":[34,62,154],"train":[35,63],"set":[37,65],"of":[38,66,70,143,158],"average":[39],"voice":[40],"model(AVM)":[41],"based":[42],"on":[43,140],"DNN":[44,68,90],"from":[45],"large":[47],"multi-speaker":[49],"corpus":[50],"small":[53],"one-speaker":[55],"corpus.":[56,132],"adaption":[59],"is":[60,83],"adopted":[61],"speaker-dependent":[67,89],"models":[69],"or":[72,80],"appended":[74],"with":[75,128,161],"AVM.":[76],"then":[84],"synthesized":[85,101,144],"their":[87],"respective":[88],"acoustic":[91],"models.":[92],"Both":[93],"subjective":[94],"evaluations":[95],"objective":[97],"tests":[98],"show":[99],"that":[100],"method":[107,150],"not":[109],"only":[110,129],"better":[111,121],"than":[112,122],"traditional":[114],"Hidden":[115],"Markov":[116],"Model(HMM)-based":[117],"method,":[118],"but":[119],"also":[120],"DNN-based":[124],"training":[131,135],"Mixed":[133],"have":[137],"little":[138],"effect":[139],"quality":[142],"speech.":[146],"Therefore,":[147],"can":[151],"be":[152],"applied":[153],"minority":[159],"language":[160],"rare":[162],"resources.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}