{"id":"https://openalex.org/W3008691130","doi":"https://doi.org/10.1109/asru46091.2019.9003829","title":"Controlling Emotion Strength with Relative Attribute for End-to-End Speech Synthesis","display_name":"Controlling Emotion Strength with Relative Attribute for End-to-End Speech Synthesis","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008691130","doi":"https://doi.org/10.1109/asru46091.2019.9003829","mag":"3008691130"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9003829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003829","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/A5014440768","display_name":"Xiaolian Zhu","orcid":"https://orcid.org/0000-0002-8842-7329"},"institutions":[{"id":"https://openalex.org/I113992204","display_name":"Hebei University of Economics and Business","ror":"https://ror.org/05j1kc284","country_code":"CN","type":"education","lineage":["https://openalex.org/I113992204"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolian Zhu","raw_affiliation_strings":["Public Computer Education Center, Hebei University of Economics and Business, Shijiazhuang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Public Computer Education Center, Hebei University of Economics and Business, Shijiazhuang, China","institution_ids":["https://openalex.org/I113992204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101736420","display_name":"Shan Yang","orcid":"https://orcid.org/0000-0003-4464-146X"},"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":"Shan Yang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611282","display_name":"Geng Yang","orcid":"https://orcid.org/0000-0002-8685-5426"},"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":"Geng Yang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7598,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.94763965,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"192","last_page":"199"},"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":0.996399998664856,"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":0.9922000169754028,"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/controllability","display_name":"Controllability","score":0.7376202344894409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7314879298210144},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5811226963996887},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.572604238986969},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5678519010543823},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4566574990749359},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.4507116377353668},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.4504276216030121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2749006152153015},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13507378101348877}],"concepts":[{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.7376202344894409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7314879298210144},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5811226963996887},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.572604238986969},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5678519010543823},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4566574990749359},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4507116377353668},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.4504276216030121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2749006152153015},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13507378101348877},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9003829","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9003829","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1501669607","https://openalex.org/W1522301498","https://openalex.org/W2090777335","https://openalex.org/W2098421901","https://openalex.org/W2125560515","https://openalex.org/W2147898188","https://openalex.org/W2294130536","https://openalex.org/W2398561585","https://openalex.org/W2591927543","https://openalex.org/W2599621350","https://openalex.org/W2604184139","https://openalex.org/W2759925408","https://openalex.org/W2770743791","https://openalex.org/W2777302760","https://openalex.org/W2785364623","https://openalex.org/W2787378487","https://openalex.org/W2793479148","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2884607399","https://openalex.org/W2885800352","https://openalex.org/W2892140764","https://openalex.org/W2893395812","https://openalex.org/W2901997113","https://openalex.org/W2904459034","https://openalex.org/W2936103087","https://openalex.org/W2937870435","https://openalex.org/W2938102059","https://openalex.org/W2945544731","https://openalex.org/W2948238043","https://openalex.org/W2952269766","https://openalex.org/W2963272440","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964121744","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2964281804","https://openalex.org/W4295731579","https://openalex.org/W6631190155","https://openalex.org/W6674701202","https://openalex.org/W6678800043","https://openalex.org/W6713020357","https://openalex.org/W6734815144","https://openalex.org/W6750489868","https://openalex.org/W6756197946","https://openalex.org/W6762643587","https://openalex.org/W6763316926"],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"Recently,":[0],"attention-based":[1],"end-to-end":[2,31,140],"speech":[3,12,69],"synthesis":[4,13],"has":[5],"achieved":[6],"superior":[7],"performance":[8,39],"compared":[9],"to":[10,24,49,103],"traditional":[11],"models,":[14],"and":[15,43,75,86,122],"several":[16],"approaches":[17],"like":[18],"global":[19],"style":[20,27,41],"tokens":[21],"are":[22],"proposed":[23],"explore":[25],"the":[26,30,34,51,64,72,104,116,135],"controllability":[28,136],"of":[29,54,67],"model.":[32,141],"Although":[33],"existing":[35],"methods":[36],"show":[37,128],"good":[38],"in":[40],"disentanglement":[42],"transfer,":[44],"it":[45],"is":[46,96],"still":[47],"unable":[48],"control":[50,66],"explicit":[52],"emotion":[53,73,110,125],"generated":[55],"speech.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"mainly":[61],"focus":[62],"on":[63,108],"subtle":[65,124],"expressive":[68,139],"synthesis,":[70],"where":[71],"category":[74],"strength":[76,94],"can":[77,132],"be":[78],"easily":[79],"controlled":[80],"with":[81],"a":[82,87,99],"discrete":[83],"emotional":[84],"vector":[85],"continuous":[88,93],"simple":[89],"scalar,":[90],"respectively.":[91],"The":[92],"controller":[95],"learned":[97],"by":[98],"ranking":[100],"function":[101],"according":[102],"relative":[105],"attribute":[106],"measured":[107],"an":[109,138],"dataset.":[111],"Our":[112],"method":[113,131],"automatically":[114],"learns":[115],"relationship":[117],"between":[118],"low-level":[119],"acoustic":[120],"features":[121],"high-level":[123],"strength.":[126],"Experiments":[127],"that":[129],"our":[130],"effectively":[133],"improve":[134],"for":[137]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}