{"id":"https://openalex.org/W4385822372","doi":"https://doi.org/10.21437/interspeech.2023-2326","title":"UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data","display_name":"UnitSpeech: Speaker-adaptive Speech Synthesis with Untranscribed Data","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822372","doi":"https://doi.org/10.21437/interspeech.2023-2326"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-2326","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2326","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/A5039955611","display_name":"Heeseung Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heeseung Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327688","display_name":"Sung\u2010Won Kim","orcid":"https://orcid.org/0000-0001-5455-6926"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungwon Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102529529","display_name":"Jiheum Yeom","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiheum Yeom","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086877012","display_name":"Sungroh Yoon","orcid":"https://orcid.org/0000-0002-2367-197X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sungroh Yoon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2632,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.93557376,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3038","last_page":"3042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9635000228881836,"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":0.9624999761581421,"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/computer-science","display_name":"Computer science","score":0.8060592412948608},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7843501567840576},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5667670965194702},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4441239833831787},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4385721981525421},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4356168508529663},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3979994058609009},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3843579888343811}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060592412948608},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7843501567840576},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5667670965194702},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4441239833831787},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4385721981525421},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4356168508529663},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3979994058609009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3843579888343811}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-2326","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-2326","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2059891707","https://openalex.org/W3087422378","https://openalex.org/W2020970176","https://openalex.org/W3120512183","https://openalex.org/W2111874347","https://openalex.org/W642007152","https://openalex.org/W2122924390","https://openalex.org/W3209889267","https://openalex.org/W1652729136","https://openalex.org/W2278654791"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
