{"id":"https://openalex.org/W3174482005","doi":"https://doi.org/10.48550/arxiv.2106.11171","title":"UniTTS: Residual Learning of Unified Embedding Space for Speech Style Control","display_name":"UniTTS: Residual Learning of Unified Embedding Space for Speech Style Control","publication_year":2021,"publication_date":"2021-06-21","ids":{"openalex":"https://openalex.org/W3174482005","doi":"https://doi.org/10.48550/arxiv.2106.11171","mag":"3174482005"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2106.11171","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.11171","pdf_url":"https://arxiv.org/pdf/2106.11171","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2106.11171","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062867075","display_name":"Minsu Kang","orcid":"https://orcid.org/0000-0003-4362-2080","observed_orcids":["https://orcid.org/0000-0003-4362-2080","https://orcid.org/0009-0001-1449-9274"]},"institutions":[{"id":"https://openalex.org/I113825674","display_name":"Handong Global University","ror":"https://ror.org/00txhkt32","country_code":"KR","type":"education","lineage":["https://openalex.org/I113825674"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kang, Minsu","raw_affiliation_strings":["Department of Computer Science and Electronic Engineering Handong Global University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Electronic Engineering Handong Global University","institution_ids":["https://openalex.org/I113825674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100618911","display_name":"Sung-Jae Kim","orcid":"https://orcid.org/0000-0003-1951-4784","observed_orcids":["https://orcid.org/0000-0003-1951-4784","https://orcid.org/0000-0003-0546-494X"]},"institutions":[{"id":"https://openalex.org/I113825674","display_name":"Handong Global University","ror":"https://ror.org/00txhkt32","country_code":"KR","type":"education","lineage":["https://openalex.org/I113825674"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Sungjae","raw_affiliation_strings":["Department of Computer Science and Electronic Engineering Handong Global University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Electronic Engineering Handong Global University","institution_ids":["https://openalex.org/I113825674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009028758","display_name":"Injung Kim","orcid":"https://orcid.org/0000-0003-4439-6097","observed_orcids":["https://orcid.org/0000-0003-4439-6097"]},"institutions":[{"id":"https://openalex.org/I113825674","display_name":"Handong Global University","ror":"https://ror.org/00txhkt32","country_code":"KR","type":"education","lineage":["https://openalex.org/I113825674"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Injung","raw_affiliation_strings":["Department of Computer Science and Electronic Engineering Handong Global University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Electronic Engineering Handong Global University","institution_ids":["https://openalex.org/I113825674"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I113825674"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.00039999998989515007,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/expressive-speech-synthesis","display_name":"expressive speech synthesis","score":0.859000027179718},{"id":"https://openalex.org/keywords/residual-learning","display_name":"residual learning","score":0.7369999885559082},{"id":"https://openalex.org/keywords/emotion-control","display_name":"emotion control","score":0.7210000157356262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7481329441070557},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7068232297897339},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6814270615577698},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.673708438873291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6188303828239441},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5936734676361084},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.524594247341156},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.48242315649986267},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4306046664714813},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3357616662979126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3182552456855774},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15033406019210815},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2106.11171","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.11171","pdf_url":"https://arxiv.org/pdf/2106.11171","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2106.11171","doi":"https://doi.org/10.48550/arxiv.2106.11171","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2106.11171","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2106.11171","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2106.11171","pdf_url":"https://arxiv.org/pdf/2106.11171","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5987044941","display_name":null,"funder_award_id":"10080667","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"},{"id":"https://openalex.org/G7399891286","display_name":null,"funder_award_id":"2017-0-00130","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320325831","display_name":"Handong Global University","ror":null},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3174482005.pdf","grobid_xml":"https://content.openalex.org/works/W3174482005.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W3133185996"],"related_works":["https://openalex.org/W4415135890","https://openalex.org/W4376457142","https://openalex.org/W2794490148","https://openalex.org/W7166886664","https://openalex.org/W4412945647","https://openalex.org/W2897548994","https://openalex.org/W3197704090","https://openalex.org/W4385822778","https://openalex.org/W3200540417","https://openalex.org/W4403780871"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,25,106],"novel":[3],"high-fidelity":[4,118],"expressive":[5],"speech":[6,119,127],"synthesis":[7],"model,":[8],"UniTTS,":[9],"that":[10,53,97,108],"learns":[11],"and":[12,38,63,75,77,82,89],"controls":[13],"overlapping":[14],"style":[15,22,123],"attributes":[16,23,52,103],"avoiding":[17],"interference.":[18],"UniTTS":[19,116],"represents":[20],"multiple":[21,51,102,122],"in":[24,49,72,105],"single":[26],"unified":[27],"embedding":[28],"space":[29],"by":[30],"the":[31,34,41,86,93,98],"residuals":[32],"between":[33],"phoneme":[35],"embeddings":[36],"before":[37],"after":[39],"applying":[40],"attributes.":[42,124],"The":[43,125],"proposed":[44,99],"method":[45],"is":[46],"especially":[47],"effective":[48],"controlling":[50,121],"are":[54,129],"difficult":[55],"to":[56],"separate":[57],"cleanly,":[58],"such":[59],"as":[60],"speaker":[61,73,87],"ID":[62,74,88],"emotion,":[64,76],"because":[65],"it":[66],"minimizes":[67],"redundancy":[68],"when":[69],"adding":[70],"variance":[71],"additionally,":[78],"predicts":[79],"duration,":[80],"pitch,":[81],"energy":[83],"based":[84],"on":[85],"emotion.":[90],"In":[91],"experiments,":[92],"visualization":[94],"results":[95],"exhibit":[96],"methods":[100],"learned":[101],"harmoniously":[104],"manner":[107],"can":[109],"be":[110],"easily":[111],"separated":[112],"again.":[113],"As":[114],"well,":[115],"synthesized":[117,126],"signals":[120],"samples":[128],"presented":[130],"at":[131],"https://anonymous-authors2022.github.io/paper_works/UniTTS/demos/.":[132]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-07-05T00:00:00"}