{"id":"https://openalex.org/W4385993887","doi":"https://doi.org/10.21437/ssw.2023-23","title":"Improving the quality of neural TTS using long-form content and multi-speaker multi-style modeling","display_name":"Improving the quality of neural TTS using long-form content and multi-speaker multi-style modeling","publication_year":2023,"publication_date":"2023-08-18","ids":{"openalex":"https://openalex.org/W4385993887","doi":"https://doi.org/10.21437/ssw.2023-23"},"language":"en","primary_location":{"id":"doi:10.21437/ssw.2023-23","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2023-23","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000571465","display_name":"Tuomo Raitio","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuomo Raitio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071418947","display_name":"Javier Latorre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Latorre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102498800","display_name":"Andrea Davis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrea Davis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062140723","display_name":"Tuuli Morrill","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tuuli Morrill","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5010570444","display_name":"Ladan Golipour","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ladan Golipour","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.8906999826431274,"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/T10320","display_name":"Neural Networks and Applications","score":0.8906999826431274,"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":0.7423151731491089},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6261701583862305},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6171025633811951},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5864095091819763},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45934540033340454},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4481123387813568},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43283700942993164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3463493585586548},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08422160148620605}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423151731491089},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6261701583862305},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6171025633811951},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5864095091819763},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45934540033340454},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4481123387813568},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43283700942993164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3463493585586548},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08422160148620605},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/ssw.2023-23","is_oa":false,"landing_page_url":"https://doi.org/10.21437/ssw.2023-23","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2356229341","https://openalex.org/W2349768204","https://openalex.org/W4313326281","https://openalex.org/W574867512","https://openalex.org/W2387271333","https://openalex.org/W4250539519","https://openalex.org/W581389233","https://openalex.org/W2361120309","https://openalex.org/W632157940","https://openalex.org/W2356684049"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}