{"id":"https://openalex.org/W4385993857","doi":"https://doi.org/10.21437/ssw.2023-19","title":"Local Style Tokens: Fine-Grained Prosodic Representations For TTS Expressive Control","display_name":"Local Style Tokens: Fine-Grained Prosodic Representations For TTS Expressive Control","publication_year":2023,"publication_date":"2023-08-18","ids":{"openalex":"https://openalex.org/W4385993857","doi":"https://doi.org/10.21437/ssw.2023-19"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2023-19","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2023-19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"12th ISCA Speech Synthesis Workshop (SSW2023)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04257713v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002601733","display_name":"Martin Lenglet","orcid":"https://orcid.org/0000-0002-3359-6846"},"institutions":[{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Martin Lenglet","raw_affiliation_strings":["GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013177566","display_name":"Olivier Perrotin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Perrotin","raw_affiliation_strings":["GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071432574","display_name":"G\u00e9rard Bailly","orcid":"https://orcid.org/0000-0002-6053-0818"},"institutions":[{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G\u00e9rard Bailly","raw_affiliation_strings":["GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210124956"],"apc_list":null,"apc_paid":null,"fwci":0.6516,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68305161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"120","last_page":"126"},"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":0.9995999932289124,"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":0.9994999766349792,"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":0.7788315415382385},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.7467265129089355},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7221832871437073},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7200567722320557},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.638146698474884},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5805940628051758},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.5312305092811584},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.48625266551971436},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.48585245013237},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47790417075157166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39656010270118713},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14447999000549316},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08928009867668152},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08229893445968628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788315415382385},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.7467265129089355},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7221832871437073},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7200567722320557},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.638146698474884},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5805940628051758},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.5312305092811584},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.48625266551971436},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.48585245013237},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47790417075157166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39656010270118713},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14447999000549316},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08928009867668152},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08229893445968628},{"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/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":2,"locations":[{"id":"doi:10.21437/ssw.2023-19","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2023-19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"12th ISCA Speech Synthesis Workshop (SSW2023)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04257713v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04257713","pdf_url":"https://hal.science/hal-04257713v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ssw2023.org/","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04257713v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04257713","pdf_url":"https://hal.science/hal-04257713v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://ssw2023.org/","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1041279674","display_name":"MIAI @ Grenoble Alpes","funder_award_id":"ANR-19-P3IA-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385993857.pdf","grobid_xml":"https://content.openalex.org/works/W4385993857.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2107860279","https://openalex.org/W2141340689","https://openalex.org/W2540285784","https://openalex.org/W2600829178","https://openalex.org/W2603532017","https://openalex.org/W2791686384","https://openalex.org/W2794490148","https://openalex.org/W2896457183","https://openalex.org/W2904459034","https://openalex.org/W2952269766","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W3033411150","https://openalex.org/W3092028330","https://openalex.org/W3096457008","https://openalex.org/W3159045181","https://openalex.org/W3183320562","https://openalex.org/W3195202172","https://openalex.org/W3200540417","https://openalex.org/W4294721141","https://openalex.org/W4295731579","https://openalex.org/W4297841537","https://openalex.org/W4309981764","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W258725851","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W1984347656","https://openalex.org/W2946856121","https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W2108985546","https://openalex.org/W2081919107"],"abstract_inverted_index":{"International":[0],"audience":[1]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
