{"id":"https://openalex.org/W2939913319","doi":"https://doi.org/10.1109/icassp.2019.8682535","title":"Phoneme Dependent Speaker Embedding and Model Factorization for Multi-speaker Speech Synthesis and Adaptation","display_name":"Phoneme Dependent Speaker Embedding and Model Factorization for Multi-speaker Speech Synthesis and Adaptation","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939913319","doi":"https://doi.org/10.1109/icassp.2019.8682535","mag":"2939913319"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5073918837","display_name":"Ruibo Fu","orcid":"https://orcid.org/0000-0001-9598-1881"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibo Fu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China","institution_ids":["https://openalex.org/I4210097554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101398585","display_name":"Yibin Zheng","orcid":"https://orcid.org/0000-0001-9158-1813"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yibin Zheng","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6930","last_page":"6934"},"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/T11309","display_name":"Music and Audio Processing","score":0.9962000250816345,"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/T10860","display_name":"Speech and Audio Processing","score":0.9950000047683716,"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":0.8248580694198608},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7665820121765137},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5839338302612305},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5765740871429443},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5246805548667908},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5184932947158813},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.48610925674438477},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.469105064868927},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.45410996675491333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4218299686908722}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248580694198608},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7665820121765137},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5839338302612305},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5765740871429443},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5246805548667908},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5184932947158813},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.48610925674438477},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.469105064868927},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.45410996675491333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4218299686908722},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W567546468","https://openalex.org/W1492383498","https://openalex.org/W1499332833","https://openalex.org/W1524333225","https://openalex.org/W1576227399","https://openalex.org/W1600722501","https://openalex.org/W2025638820","https://openalex.org/W2046056978","https://openalex.org/W2094147890","https://openalex.org/W2095705004","https://openalex.org/W2102003408","https://openalex.org/W2129142580","https://openalex.org/W2134973740","https://openalex.org/W2150658333","https://openalex.org/W2271840356","https://openalex.org/W2294797155","https://openalex.org/W2401698713","https://openalex.org/W2471520273","https://openalex.org/W2494654097","https://openalex.org/W2516559027","https://openalex.org/W2605320104","https://openalex.org/W2746498480","https://openalex.org/W2889226978","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W4235154690","https://openalex.org/W6600284362","https://openalex.org/W6615969787","https://openalex.org/W6631362777","https://openalex.org/W6674330103","https://openalex.org/W6675380101","https://openalex.org/W6694517276"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,62,94,98,104],"architecture":[4],"to":[5,67,73],"perform":[6],"speaker":[7,32,38,45,79,112,126,152],"adaption":[8],"in":[9,34,47,58,147],"long":[10],"short-term":[11],"memory":[12],"(LSTM)":[13],"based":[14],"Mandarin":[15],"statistical":[16],"parametric":[17],"speech":[18],"synthesis":[19],"system.":[20],"Compared":[21],"with":[22],"the":[23,41,83,89,109,121],"conventional":[24],"methods":[25],"that":[26,136],"focused":[27],"on":[28],"using":[29],"fixed":[30],"global":[31],"representations":[33,46,71,113],"utterance":[35,48],"level":[36,70],"for":[37],"recognition":[39],"task,":[40],"proposed":[42,125,138],"method":[43,139],"extracts":[44],"and":[49,86,97,101,128,151],"phoneme":[50,59,77],"level,":[51],"which":[52],"can":[53,140],"describe":[54],"more":[55],"pronunciation":[56],"characteristics":[57],"level.":[60],"And":[61,132],"attention":[63,105],"mechanism":[64],"is":[65,91],"deployed":[66],"combine":[68],"each":[69],"dynamically":[72],"train":[74],"a":[75],"task-specific":[76],"dependent":[78],"embedding.":[80],"To":[81],"handle":[82],"unbalanced":[84],"database":[85],"avoid":[87],"over-fitting,":[88],"model":[90,96,100,129],"factored":[92],"into":[93],"average":[95],"adaptation":[99,143],"combined":[102],"by":[103,115],"mechanism.":[106],"We":[107],"investigate":[108],"performance":[110,144],"of":[111,123,149],"extracted":[114],"different":[116],"methods.":[117],"Experimental":[118],"results":[119],"confirm":[120],"adaptability":[122],"our":[124,137],"embedding":[127],"factorization":[130],"structure.":[131],"listening":[133],"tests":[134],"demonstrate":[135],"achieve":[141],"better":[142],"than":[145],"baselines":[146],"terms":[148],"naturalness":[150],"similarity.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}