{"id":"https://openalex.org/W3205631867","doi":"https://doi.org/10.1109/icassp43922.2022.9747747","title":"Fine-Grained Style Control In Transformer-Based Text-To-Speech Synthesis","display_name":"Fine-Grained Style Control In Transformer-Based Text-To-Speech Synthesis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3205631867","doi":"https://doi.org/10.1109/icassp43922.2022.9747747","mag":"3205631867"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747747","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5100625784","display_name":"Liwei Chen","orcid":"https://orcid.org/0000-0002-9858-0765"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Li-Wei Chen","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040668817","display_name":"Alexander I. Rudnicky","orcid":"https://orcid.org/0000-0003-2044-8446"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Rudnicky","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100625784"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.8246,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92171516,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7907","last_page":"7911"},"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":0.9973000288009644,"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/T12031","display_name":"Speech and dialogue systems","score":0.996999979019165,"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":0.683402955532074},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6717702746391296},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6321104764938354},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.605473518371582},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4944589138031006},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4927704632282257},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.47728338837623596},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4682152271270752},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42582860589027405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3617973327636719},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08096012473106384}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.683402955532074},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6717702746391296},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6321104764938354},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.605473518371582},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4944589138031006},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4927704632282257},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.47728338837623596},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4682152271270752},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42582860589027405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3617973327636719},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08096012473106384},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747747","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747747","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2064675550","https://openalex.org/W2794490148","https://openalex.org/W2795109282","https://openalex.org/W2896457183","https://openalex.org/W2903739847","https://openalex.org/W2946200149","https://openalex.org/W2962780374","https://openalex.org/W2963272440","https://openalex.org/W2963300588","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2963927338","https://openalex.org/W2964121744","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2970730223","https://openalex.org/W2973158936","https://openalex.org/W2998572311","https://openalex.org/W3015212100","https://openalex.org/W3033194228","https://openalex.org/W3034837210","https://openalex.org/W3036601975","https://openalex.org/W3095545636","https://openalex.org/W3099782249","https://openalex.org/W3135644023","https://openalex.org/W3152136404","https://openalex.org/W3160329778","https://openalex.org/W3163573274","https://openalex.org/W3198609073","https://openalex.org/W3198791321","https://openalex.org/W4295731579","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6736996214","https://openalex.org/W6739901393","https://openalex.org/W6750489868","https://openalex.org/W6755207826","https://openalex.org/W6763832098","https://openalex.org/W6772349387","https://openalex.org/W6780218876","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2079655441","https://openalex.org/W2912293245","https://openalex.org/W1604114751","https://openalex.org/W4252942110","https://openalex.org/W2032941915","https://openalex.org/W2075706796","https://openalex.org/W2549308614","https://openalex.org/W3018584924","https://openalex.org/W2023694213","https://openalex.org/W2958354987"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,20,90],"present":[4],"a":[5,27,75,86],"novel":[6],"architecture":[7],"to":[8,79],"realize":[9],"fine-grained":[10,114],"style":[11,24,32,93,115,127],"control":[12],"on":[13],"the":[14,22,36,62,68,82,92],"transformer-based":[15],"text-to-speech":[16],"synthesis":[17],"(TransformerTTS).":[18],"Specifically,":[19],"model":[21],"speaking":[23],"by":[25,48,99],"extracting":[26],"time":[28],"sequence":[29],"of":[30,123],"local":[31],"tokens":[33],"(LST)":[34],"from":[35,95],"reference":[37],"speech.":[38],"The":[39],"existing":[40],"content":[41,58,98],"encoder":[42],"in":[43,121],"TransformerTTS":[44],"is":[45,64],"then":[46],"replaced":[47],"our":[49,71,117],"designed":[50],"cross-attention":[51,72],"blocks":[52],"for":[53],"fusion":[54,63],"and":[55,59,105,126,131],"alignment":[56],"between":[57],"style.":[60,88],"As":[61],"performed":[65],"along":[66],"with":[67,85,113],"skip":[69],"connection,":[70],"block":[73],"provides":[74],"good":[76],"inductive":[77],"bias":[78],"gradually":[80],"infuse":[81],"phoneme":[83],"representation":[84],"given":[87],"Additionally,":[89],"prevent":[91],"embedding":[94],"encoding":[96],"linguistic":[97],"randomly":[100],"truncating":[101],"LST":[102],"during":[103],"training":[104],"using":[106],"wav2vec":[107],"2.0":[108],"features.":[109],"Experiments":[110],"show":[111],"that":[112],"control,":[116],"system":[118],"performs":[119],"better":[120],"terms":[122],"naturalness,":[124],"intelligibility,":[125],"transferability.":[128],"Our":[129],"code":[130],"samples":[132],"are":[133],"publicly":[134],"available.":[135],"<sup":[136],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[137],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[138]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}