{"id":"https://openalex.org/W4415433731","doi":"https://doi.org/10.21437/interspeech.2025-433","title":"When Humans Growl and Birds Speak: High-Fidelity Voice Conversion from Human to Animal and Designed Sounds","display_name":"When Humans Growl and Birds Speak: High-Fidelity Voice Conversion from Human to Animal and Designed Sounds","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433731","doi":"https://doi.org/10.21437/interspeech.2025-433"},"language":null,"primary_location":{"id":"doi:10.21437/interspeech.2025-433","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-433","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/A5062867075","display_name":"Minsu Kang","orcid":"https://orcid.org/0000-0003-4362-2080"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Minsu Kang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084453279","display_name":"Seolhee Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seolhee Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057261199","display_name":"Choonghyeon Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choonghyeon Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020960851","display_name":"Nam Hyun Cho","orcid":"https://orcid.org/0000-0002-7188-0565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Namhyun Cho","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062867075"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8331,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.92835621,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4153","last_page":"4157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.7817000150680542,"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/T12031","display_name":"Speech and dialogue systems","score":0.7817000150680542,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.7192000150680542,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.6669999957084656,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sound-production","display_name":"Sound production","score":0.3921000063419342},{"id":"https://openalex.org/keywords/animal-communication","display_name":"Animal communication","score":0.3400000035762787},{"id":"https://openalex.org/keywords/bioacoustics","display_name":"Bioacoustics","score":0.3224000036716461},{"id":"https://openalex.org/keywords/human-voice","display_name":"Human voice","score":0.2630000114440918}],"concepts":[{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4153999984264374},{"id":"https://openalex.org/C2992428333","wikidata":"https://www.wikidata.org/wiki/Q11461","display_name":"Sound production","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3409999907016754},{"id":"https://openalex.org/C59726852","wikidata":"https://www.wikidata.org/wiki/Q1434121","display_name":"Animal communication","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C20766975","wikidata":"https://www.wikidata.org/wiki/Q7390","display_name":"Human voice","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24869999289512634},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2459000051021576},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2433999925851822}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2025-433","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-433","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}