{"id":"https://openalex.org/W4402112526","doi":"https://doi.org/10.21437/interspeech.2024-2504","title":"Challenge of Singing Voice Synthesis Using Only Text-To-Speech Corpus With FIRNet Source-Filter Neural Vocoder","display_name":"Challenge of Singing Voice Synthesis Using Only Text-To-Speech Corpus With FIRNet Source-Filter Neural Vocoder","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402112526","doi":"https://doi.org/10.21437/interspeech.2024-2504"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-2504","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","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/A5022943637","display_name":"Takuma Okamoto","orcid":"https://orcid.org/0000-0001-9913-4647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018533235","display_name":"Yamato Ohtani","orcid":"https://orcid.org/0009-0009-2961-2821"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yamato Ohtani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067228682","display_name":"Sota Shimizu","orcid":"https://orcid.org/0009-0006-2296-4443"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sota Shimizu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103146649","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0003-3789-4055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","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":"1870","last_page":"1874"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958000183105469,"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":0.9958000183105469,"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/T11309","display_name":"Music and Audio Processing","score":0.9900000095367432,"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/T10860","display_name":"Speech and Audio Processing","score":0.9807999730110168,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.762660801410675},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7308556437492371},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7095789313316345},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6307264566421509},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.505237877368927},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37302854657173157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36059921979904175},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23627695441246033},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05111879110336304}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.762660801410675},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7308556437492371},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7095789313316345},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6307264566421509},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.505237877368927},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37302854657173157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36059921979904175},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23627695441246033},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05111879110336304},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-2504","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-2504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W2366077683","https://openalex.org/W1501596003","https://openalex.org/W127416991"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
