{"id":"https://openalex.org/W4385822575","doi":"https://doi.org/10.21437/interspeech.2023-1673","title":"Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS","display_name":"Stochastic Pitch Prediction Improves the Diversity and Naturalness of Speech in Glow-TTS","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822575","doi":"https://doi.org/10.21437/interspeech.2023-1673"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1673","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1673","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/A5087685199","display_name":"Sewade Ogun","orcid":null},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Sewade Ogun","raw_affiliation_strings":["MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (Centre Inria de l'Universit\u00e9 de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-l\u00e8s-Nancy - France)"],"affiliations":[{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (Centre Inria de l'Universit\u00e9 de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-l\u00e8s-Nancy - France)","institution_ids":["https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039712983","display_name":"Vincent Colotte","orcid":null},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Colotte","raw_affiliation_strings":["MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (Centre Inria de l'Universit\u00e9 de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-l\u00e8s-Nancy - France)"],"affiliations":[{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (Centre Inria de l'Universit\u00e9 de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-l\u00e8s-Nancy - France)","institution_ids":["https://openalex.org/I90183372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065635001","display_name":"Emmanuel Vincent","orcid":"https://orcid.org/0000-0002-0183-7289"},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Vincent","raw_affiliation_strings":["MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (Centre Inria de l'Universit\u00e9 de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-l\u00e8s-Nancy - France)"],"affiliations":[{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (Centre Inria de l'Universit\u00e9 de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-l\u00e8s-Nancy - France)","institution_ids":["https://openalex.org/I90183372"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087685199"],"corresponding_institution_ids":["https://openalex.org/I90183372"],"apc_list":null,"apc_paid":null,"fwci":0.4075,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.56557121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4878","last_page":"4882"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9492999911308289,"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/naturalness","display_name":"Naturalness","score":0.9027588367462158},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5923465490341187},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5749132037162781},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5336989164352417},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.4131011664867401},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1473676562309265},{"id":"https://openalex.org/keywords/particle-physics","display_name":"Particle physics","score":0.053702473640441895}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9027588367462158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5923465490341187},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5749132037162781},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5336989164352417},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.4131011664867401},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1473676562309265},{"id":"https://openalex.org/C109214941","wikidata":"https://www.wikidata.org/wiki/Q18334","display_name":"Particle physics","level":1,"score":0.053702473640441895},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1673","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1673","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W1537411440","https://openalex.org/W1984347656","https://openalex.org/W2535215250","https://openalex.org/W2024201202"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
