{"id":"https://openalex.org/W4415432988","doi":"https://doi.org/10.21437/interspeech.2025-1940","title":"Investigating Stochastic Methods for Prosody Modeling in Speech Synthesis","display_name":"Investigating Stochastic Methods for Prosody Modeling in Speech Synthesis","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415432988","doi":"https://doi.org/10.21437/interspeech.2025-1940"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-1940","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","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/A5112335026","display_name":"Paul Mayer","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Paul Mayer","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078880407","display_name":"Florian Lux","orcid":"https://orcid.org/0000-0003-4325-5129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florian Lux","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091092804","display_name":"Alejandro P\u00e9rez-Gonz\u00e1lez-de-Martos","orcid":"https://orcid.org/0000-0002-0453-2114"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alejandro P\u00e9rez-Gonz\u00e1lez-de-Martos","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019086642","display_name":"Anastasia Elizarova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Angelina Elizarova","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034325503","display_name":"Lindsey Vanderlyn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lindsey Vanderlyn","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067655012","display_name":"Dirk V\u00e4th","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dirk V\u00e4th","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020700841","display_name":"Ngoc Thang Vu","orcid":"https://orcid.org/0000-0001-7893-9147"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ngoc Thang Vu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5112335026"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16654189,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"439","last_page":"443"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9729999899864197,"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":0.9729999899864197,"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/T12031","display_name":"Speech and dialogue systems","score":0.9660999774932861,"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":0.6126000285148621},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.44269999861717224},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.299699991941452},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2980000078678131},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.27250000834465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6276000142097473},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6126000285148621},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5440000295639038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45660001039505005},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43290001153945923},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2980000078678131},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-1940","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-1940","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","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":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}