{"id":"https://openalex.org/W4385822637","doi":"https://doi.org/10.21437/interspeech.2023-834","title":"Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech","display_name":"Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822637","doi":"https://doi.org/10.21437/interspeech.2023-834"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-834","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-834","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":"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/A5102854878","display_name":"Guangyan Zhang","orcid":"https://orcid.org/0000-0002-3480-5902"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guangyan Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038417409","display_name":"Thomas Merritt","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Merritt","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102545089","display_name":"Sam Ribeiro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sam Ribeiro","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092579799","display_name":"Biel Tura-Vecino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biel Tura-Vecino","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047287498","display_name":"Kayoko Yanagisawa","orcid":"https://orcid.org/0000-0002-3444-7287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kayoko Yanagisawa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000904701","display_name":"Kamil Pokora","orcid":"https://orcid.org/0009-0006-0756-4118"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kamil Pokora","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027412678","display_name":"Abdelhamid Ezzerg","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abdelhamid Ezzerg","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069232913","display_name":"Sebastian Cygert","orcid":"https://orcid.org/0000-0002-4763-8381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sebastian Cygert","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","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":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060480943","display_name":"Piotr Bili\u0144ski","orcid":"https://orcid.org/0000-0002-7023-3438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piotr Bilinski","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027755752","display_name":"Roberto Barra-Chicote","orcid":"https://orcid.org/0000-0003-0844-7037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Barra-Chicote","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039620116","display_name":"Daniel Korzekwa","orcid":"https://orcid.org/0000-0003-1470-4968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Korzekwa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5102854878"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09389629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9739000201225281,"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":0.9739000201225281,"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":0.8059934377670288},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.676979124546051},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.6106473207473755},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5802449584007263},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4613369405269623},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1091107726097107}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8059934377670288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676979124546051},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6106473207473755},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5802449584007263},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4613369405269623},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1091107726097107},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-834","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-834","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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W3149582125","https://openalex.org/W1984347656","https://openalex.org/W157238252","https://openalex.org/W2169632867","https://openalex.org/W2465421051","https://openalex.org/W652196294","https://openalex.org/W2368700418","https://openalex.org/W1965141925"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
