{"id":"https://openalex.org/W4385823133","doi":"https://doi.org/10.21437/interspeech.2023-965","title":"eCat: An End-to-End Model for Multi-Speaker TTS &amp; Many-to-Many Fine-Grained Prosody Transfer","display_name":"eCat: An End-to-End Model for Multi-Speaker TTS &amp; Many-to-Many Fine-Grained Prosody Transfer","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823133","doi":"https://doi.org/10.21437/interspeech.2023-965"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-965","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/A5035308242","display_name":"Ammar N. Abbas","orcid":"https://orcid.org/0000-0002-2578-5137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ammar Abbas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066855316","display_name":"Sri Karlapati","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sri Karlapati","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050653844","display_name":"Bastian Schnell","orcid":"https://orcid.org/0000-0002-3540-0149"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bastian Schnell","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006537074","display_name":"Penny Karanasou","orcid":"https://orcid.org/0000-0003-1939-4161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Penny Karanasou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088871819","display_name":"Marcel Granero Moya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcel Granero Moya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112980301","display_name":"Amith Nagaraj","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amith Nagaraj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085496239","display_name":"Ayman Boustati","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayman Boustati","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056189765","display_name":"Nicole Peinelt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicole Peinelt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014483986","display_name":"Alexis Moinet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexis Moinet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Drugman","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3387","last_page":"3391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9879999756813049,"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":0.9879999756813049,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9442999958992004,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9244999885559082,"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/prosody","display_name":"Prosody","score":0.8246785402297974},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.745278000831604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.627958357334137},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.44281697273254395},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.41614586114883423},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4100835919380188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1791490614414215},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.13701122999191284}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8246785402297974},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.745278000831604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.627958357334137},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.44281697273254395},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.41614586114883423},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4100835919380188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1791490614414215},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.13701122999191284},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-965","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","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/W2355553914","https://openalex.org/W2972909277","https://openalex.org/W4380906377","https://openalex.org/W2587150483","https://openalex.org/W2972441390","https://openalex.org/W3108238911","https://openalex.org/W2546089952","https://openalex.org/W3096702609","https://openalex.org/W2972892026","https://openalex.org/W2140022733"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
