{"id":"https://openalex.org/W3007067948","doi":"https://doi.org/10.1109/asru46091.2019.9003859","title":"Learning Hierarchical Representations for Expressive Speaking Style in End-to-End Speech Synthesis","display_name":"Learning Hierarchical Representations for Expressive Speaking Style in End-to-End Speech Synthesis","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007067948","doi":"https://doi.org/10.1109/asru46091.2019.9003859","mag":"3007067948"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003859","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5042649425","display_name":"Xiaochun An","orcid":"https://orcid.org/0000-0002-8675-3980"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaochun An","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103854502","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-8269-3354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736420","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan Yang","raw_affiliation_strings":["ByteDance AI Lab"],"affiliations":[{"raw_affiliation_string":"ByteDance AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110851569","display_name":"Zejun Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042649425"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":1.8202,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.8936429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"184","last_page":"191"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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":0.9977999925613403,"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/style","display_name":"Style (visual arts)","score":0.7868798971176147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7407580614089966},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.6602393388748169},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5281389355659485},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.511819064617157},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5102994441986084},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.48445582389831543},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44258710741996765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40872448682785034}],"concepts":[{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.7868798971176147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7407580614089966},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.6602393388748169},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5281389355659485},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.511819064617157},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5102994441986084},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.48445582389831543},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44258710741996765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40872448682785034},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003859","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1972420736","https://openalex.org/W2102003408","https://openalex.org/W2107860279","https://openalex.org/W2117475030","https://openalex.org/W2120847449","https://openalex.org/W2129142580","https://openalex.org/W2187089797","https://openalex.org/W2475998840","https://openalex.org/W2516321201","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2603120115","https://openalex.org/W2651834199","https://openalex.org/W2766406951","https://openalex.org/W2769810959","https://openalex.org/W2777302760","https://openalex.org/W2793479148","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2808706139","https://openalex.org/W2885800352","https://openalex.org/W2904459034","https://openalex.org/W2949382160","https://openalex.org/W2962691331","https://openalex.org/W2963272440","https://openalex.org/W2963432880","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W4289383906","https://openalex.org/W4294619240","https://openalex.org/W4295731579","https://openalex.org/W4327693937","https://openalex.org/W6643482484","https://openalex.org/W6736996214","https://openalex.org/W6745232783","https://openalex.org/W6750489868","https://openalex.org/W6753855596","https://openalex.org/W6755300632","https://openalex.org/W7043748487"],"related_works":["https://openalex.org/W2386430105","https://openalex.org/W2356521405","https://openalex.org/W2038534795","https://openalex.org/W2384358604","https://openalex.org/W1567829292","https://openalex.org/W3001063351","https://openalex.org/W3196905815","https://openalex.org/W2351370765","https://openalex.org/W3133811809","https://openalex.org/W127416991"],"abstract_inverted_index":{"Although":[0],"Global":[1],"Style":[2],"Tokens":[3],"(GSTs)":[4],"are":[5,19],"a":[6,20,39,84,97],"recently-proposed":[7],"method":[8],"to":[9,45,52,82,86],"uncover":[10],"expressive":[11],"factors":[12],"of":[13,22,30,77,100,123],"variation":[14],"in":[15,59,113],"speaking":[16,32,105],"style,":[17],"they":[18],"mixture":[21],"style":[23,57,88,106,124],"attributes":[24],"without":[25],"explicitly":[26],"considering":[27],"the":[28,75,92,117],"factorization":[29],"multiple-level":[31,49],"styles.":[33],"In":[34],"this":[35],"work,":[36],"we":[37,80],"introduce":[38],"hierarchical":[40,64],"GST":[41,72,94],"architecture":[42],"with":[43],"residuals":[44],"Tacotron,":[46],"which":[47],"learns":[48,96],"disentangled":[50],"representations":[51],"model":[53,119],"and":[54],"control":[55],"different":[56,71],"granularities":[58],"synthesized":[60],"speech.":[61],"We":[62],"make":[63],"evaluations":[65],"conditioned":[66],"on":[67],"individual":[68],"tokens":[69],"from":[70],"layers.":[73,115],"As":[74],"number":[76],"layers":[78],"increases,":[79],"tend":[81],"observe":[83],"coarse":[85],"fine":[87],"decomposition.":[89],"For":[90],"example,":[91],"first":[93],"layer":[95],"good":[98,121],"representation":[99],"speaker":[101],"IDs":[102],"while":[103],"finer":[104],"or":[107],"emotion":[108],"variations":[109],"can":[110],"be":[111],"found":[112],"higher-level":[114],"Meanwhile,":[116],"proposed":[118],"shows":[120],"performance":[122],"transfer.":[125]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}