{"id":"https://openalex.org/W3161822901","doi":"https://doi.org/10.1109/icassp39728.2021.9414220","title":"Unsupervised Learning for Multi-Style Speech Synthesis with Limited Data","display_name":"Unsupervised Learning for Multi-Style Speech Synthesis with Limited Data","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161822901","doi":"https://doi.org/10.1109/icassp39728.2021.9414220","mag":"3161822901"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5033522290","display_name":"Shuang Liang","orcid":"https://orcid.org/0000-0001-7003-3906"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":true,"raw_author_name":"Shuang Liang","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102412218","display_name":"Chenfeng Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Chenfeng Miao","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059638789","display_name":"Minchuan Chen","orcid":"https://orcid.org/0009-0001-1512-6672"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Minchuan Chen","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100643103","display_name":"Jun Ma","orcid":"https://orcid.org/0009-0003-8713-0667"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100702017","display_name":"Shaojun Wang","orcid":"https://orcid.org/0009-0001-8955-8566"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology"],"affiliations":[{"raw_affiliation_string":"Ping An Technology","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5033522290"],"corresponding_institution_ids":["https://openalex.org/I4401726822"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52165602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"9","issue":null,"first_page":"6583","last_page":"6587"},"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/T10028","display_name":"Topic Modeling","score":0.9973000288009644,"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":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7860292196273804},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6837422847747803},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6003913283348083},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5147581100463867},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5046066045761108},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5029978156089783},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5027623176574707},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4490191340446472},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4280216097831726},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4140647351741791}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860292196273804},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6837422847747803},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6003913283348083},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5147581100463867},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5046066045761108},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5029978156089783},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5027623176574707},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4490191340446472},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4280216097831726},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4140647351741791},{"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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2187089797","https://openalex.org/W2519091744","https://openalex.org/W2770743791","https://openalex.org/W2794490148","https://openalex.org/W2798991696","https://openalex.org/W2803832867","https://openalex.org/W2808706139","https://openalex.org/W2886769154","https://openalex.org/W2892140764","https://openalex.org/W2904459034","https://openalex.org/W2950374865","https://openalex.org/W2962691331","https://openalex.org/W2962850167","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2964160479","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W3010916717","https://openalex.org/W3015212100","https://openalex.org/W3015282541","https://openalex.org/W3015440759","https://openalex.org/W3015796413","https://openalex.org/W3026435290","https://openalex.org/W4289383906","https://openalex.org/W4293469690","https://openalex.org/W6729906282","https://openalex.org/W6746238782","https://openalex.org/W6750489868","https://openalex.org/W6752051073","https://openalex.org/W6752888775","https://openalex.org/W6754925833","https://openalex.org/W6755300632","https://openalex.org/W6763984584","https://openalex.org/W6767111847"],"related_works":["https://openalex.org/W2356229341","https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W2349768204","https://openalex.org/W2142795561","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W3155418658","https://openalex.org/W4243199227"],"abstract_inverted_index":{"Existing":[0],"multi-style":[1,27,54],"speech":[2,28,72,84,107,112],"synthesis":[3,29,108,113],"methods":[4],"require":[5],"either":[6],"style":[7,45,50,75,127],"labels":[8],"or":[9],"large":[10],"amounts":[11],"of":[12],"unlabeled":[13],"training":[14,132],"data,":[15],"making":[16],"data":[17],"acquisition":[18],"difficult.":[19],"In":[20,115],"this":[21],"paper,":[22],"we":[23,57,117],"present":[24],"an":[25],"unsupervised":[26],"method":[30,78,121],"that":[31,98,119],"can":[32,70],"be":[33],"trained":[34],"with":[35,129],"limited":[36],"data.":[37],"We":[38],"leverage":[39],"instance":[40],"discriminator":[41],"to":[42,47,61,81,124],"guide":[43],"a":[44,53,86],"encoder":[46],"learn":[48,125],"meaningful":[49,126],"representations":[51],"from":[52],"dataset.":[55],"Furthermore,":[56],"employ":[58],"information":[59,65],"bottleneck":[60],"filter":[62],"out":[63],"style-irrelevant":[64],"in":[66,104],"the":[67,91],"representations,":[68],"which":[69],"improve":[71],"quality":[73],"and":[74,110],"similarity.":[76],"Our":[77],"is":[79,122],"able":[80,123],"produce":[82],"desirable":[83],"using":[85],"fairly":[87],"small":[88],"dataset,":[89],"where":[90],"baseline":[92],"GST-Tacotron":[93,103],"fails.":[94],"ABX":[95],"tests":[96],"show":[97],"our":[99,120],"model":[100],"significantly":[101],"outperforms":[102],"both":[105],"emotional":[106],"task":[109],"multi-speaker":[111],"task.":[114],"addition,":[116],"demonstrate":[118],"features":[128],"only":[130],"50":[131],"samples":[133],"per":[134],"style.":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}