{"id":"https://openalex.org/W3144044466","doi":"https://doi.org/10.1109/slt48900.2021.9383537","title":"Controllable Emphatic Speech Synthesis based on Forward Attention for Expressive Speech Synthesis","display_name":"Controllable Emphatic Speech Synthesis based on Forward Attention for Expressive Speech Synthesis","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3144044466","doi":"https://doi.org/10.1109/slt48900.2021.9383537","mag":"3144044466"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5030114271","display_name":"Liangqi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Liangqi Liu","raw_affiliation_strings":["Beijing National Research Centre for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Centre for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075234257","display_name":"Jiankun Hu","orcid":"https://orcid.org/0000-0003-0230-1432"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Jiankun Hu","raw_affiliation_strings":["Beijing National Research Centre for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Centre for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Beijing National Research Centre for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Centre for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051317379","display_name":"Song Yang","orcid":"https://orcid.org/0000-0002-5385-1402"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Yang","raw_affiliation_strings":["AI Lab, TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Lab, TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101085314","display_name":"Songfan Yang","orcid":"https://orcid.org/0000-0002-3560-3624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Songfan Yang","raw_affiliation_strings":["AI Lab, TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"AI Lab, TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405572","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0002-7336-4003"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Beijing National Research Centre for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Beijing National Research Centre for Information Science and Technology (BNRist), Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China","Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Research Center for Media Sciences, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5030114271"],"corresponding_institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77341182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"410","last_page":"414"},"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":0.9970999956130981,"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":0.9962000250816345,"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/naturalness","display_name":"Naturalness","score":0.9054417014122009},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.8200888633728027},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7928591966629028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7795254588127136},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7516369223594666},{"id":"https://openalex.org/keywords/emphasis","display_name":"Emphasis (telecommunications)","score":0.7195637822151184},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6596128940582275},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.6491755843162537},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4470948576927185},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44679689407348633},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.43677008152008057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40193286538124084},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35729724168777466},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.32855069637298584},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.26054397225379944},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11521035432815552},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06472817063331604},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.062235742807388306}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9054417014122009},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.8200888633728027},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7928591966629028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7795254588127136},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7516369223594666},{"id":"https://openalex.org/C177454536","wikidata":"https://www.wikidata.org/wiki/Q578290","display_name":"Emphasis (telecommunications)","level":2,"score":0.7195637822151184},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6596128940582275},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.6491755843162537},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4470948576927185},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44679689407348633},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.43677008152008057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40193286538124084},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35729724168777466},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.32855069637298584},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.26054397225379944},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11521035432815552},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06472817063331604},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.062235742807388306},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383537","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W45989781","https://openalex.org/W1522301498","https://openalex.org/W1560592162","https://openalex.org/W1592822300","https://openalex.org/W2048389584","https://openalex.org/W2120847449","https://openalex.org/W2133564696","https://openalex.org/W2401700297","https://openalex.org/W2584505851","https://openalex.org/W2604184139","https://openalex.org/W2619368999","https://openalex.org/W2759925408","https://openalex.org/W2808706139","https://openalex.org/W2886769154","https://openalex.org/W2890116704","https://openalex.org/W2890287821","https://openalex.org/W2893395812","https://openalex.org/W2904459034","https://openalex.org/W2936832667","https://openalex.org/W2963432880","https://openalex.org/W2963712897","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W6601891972","https://openalex.org/W6631190155","https://openalex.org/W6679434410","https://openalex.org/W6713534906","https://openalex.org/W6736356763","https://openalex.org/W6752888775","https://openalex.org/W6765987481"],"related_works":["https://openalex.org/W2535215250","https://openalex.org/W2946856121","https://openalex.org/W2349468610","https://openalex.org/W1914543332","https://openalex.org/W1984347656","https://openalex.org/W2370805772","https://openalex.org/W2772686614","https://openalex.org/W4200068392","https://openalex.org/W2036933852","https://openalex.org/W231741463"],"abstract_inverted_index":{"In":[0],"speech":[1,4,18,68,176],"interaction":[2],"scenarios,":[3],"emphasis":[5,48,120,129,160],"is":[6,108,131],"essential":[7],"for":[8,36,85,135],"expressing":[9],"the":[10,22,41,79,117,140],"underlying":[11],"intention":[12],"and":[13,51,54,65,88,113,123,126,144,163,166,173,180],"attitude.":[14],"Recently,":[15],"end-to-end":[16],"emphatic":[17,38,67,175],"synthesis":[19,69],"greatly":[20],"improves":[21],"naturalness":[23],"of":[24,34,47,82,101,119,142,159],"synthetic":[25],"speech,":[26],"but":[27,168],"also":[28,169],"brings":[29],"new":[30],"problems:":[31],"1)":[32],"lack":[33],"interpretability":[35],"how":[37],"codes":[39],"affect":[40],"model;":[42],"2)":[43],"no":[44],"separate":[45,157],"control":[46,158],"on":[49,52,72,121,124,161,164],"duration":[50,122,162],"intonation":[53,125,143,165],"energy.":[55,127,145],"We":[56],"propose":[57],"a":[58],"novel":[59],"way":[60],"to":[61,95,115],"build":[62],"an":[63],"interpretable":[64],"controllable":[66],"framework":[70],"based":[71],"forward":[73,93],"attention.":[74],"Firstly,":[75],"we":[76],"explicitly":[77],"model":[78,152],"local":[80],"variation":[81],"speaking":[83],"rate":[84],"emphasized":[86,97,137],"words":[87,90,98,138],"neutral":[89],"with":[91,177],"modified":[92],"attention":[94],"manifest":[96],"in":[99,106,139],"terms":[100],"duration.":[102],"The":[103,128],"2-layers":[104],"LSTM":[105],"decoder":[107],"further":[109],"divided":[110],"into":[111,133],"attention-RNN":[112],"decoder-RNN":[114,134],"disentangle":[116],"influence":[118],"information":[130],"injected":[132],"highlighting":[136],"aspects":[141],"Experimental":[146],"results":[147],"have":[148],"shown":[149],"that":[150],"our":[151],"can":[153],"not":[154],"only":[155],"provide":[156],"energy,":[167],"generate":[170],"more":[171],"robust":[172],"prominent":[174],"high":[178],"quality":[179],"naturalness.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}