{"id":"https://openalex.org/W4385823117","doi":"https://doi.org/10.21437/interspeech.2023-1128","title":"Hierarchical Timbre-Cadence Speaker Encoder for Zero-shot Speech Synthesis","display_name":"Hierarchical Timbre-Cadence Speaker Encoder for Zero-shot Speech Synthesis","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823117","doi":"https://doi.org/10.21437/interspeech.2023-1128"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1128","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1128","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/A5042018167","display_name":"Joun Yeop Lee","orcid":"https://orcid.org/0000-0002-3316-4808"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Joun Yeop Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060429696","display_name":"Jae\u2010sung Bae","orcid":"https://orcid.org/0000-0002-8270-0072"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jae-Sung Bae","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021831317","display_name":"Seongkyu Mun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seongkyu Mun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674127","display_name":"Jihwan Lee","orcid":"https://orcid.org/0000-0001-9380-5470"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jihwan Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413485","display_name":"Ji\u2010Hyun Lee","orcid":"https://orcid.org/0000-0001-6420-5150"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji-Hyun Lee","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052468556","display_name":"Hoon Young Cho","orcid":"https://orcid.org/0000-0002-6850-6580"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hoon-Young Cho","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5042018167"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8741,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7871684,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9958999752998352,"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":0.9958999752998352,"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/T10860","display_name":"Speech and Audio Processing","score":0.9948999881744385,"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/T11309","display_name":"Music and Audio Processing","score":0.9736999869346619,"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/cadence","display_name":"Cadence","score":0.837887167930603},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7243343591690063},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.64794921875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6190447211265564},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5731663703918457},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17623767256736755},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.12977328896522522}],"concepts":[{"id":"https://openalex.org/C2777125575","wikidata":"https://www.wikidata.org/wiki/Q14088448","display_name":"Cadence","level":2,"score":0.837887167930603},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7243343591690063},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.64794921875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6190447211265564},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5731663703918457},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17623767256736755},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.12977328896522522},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1128","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1128","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/W2275988210","https://openalex.org/W2385621972","https://openalex.org/W1901324946","https://openalex.org/W2368779261","https://openalex.org/W2589098947","https://openalex.org/W4231964008","https://openalex.org/W4384009541","https://openalex.org/W1570824959","https://openalex.org/W2149825536","https://openalex.org/W2778699561"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
