{"id":"https://openalex.org/W4385823416","doi":"https://doi.org/10.21437/interspeech.2023-391","title":"VISinger2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer","display_name":"VISinger2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizer","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823416","doi":"https://doi.org/10.21437/interspeech.2023-391"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-391","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-391","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/A5060467975","display_name":"Yongmao Zhang","orcid":"https://orcid.org/0009-0000-0526-5778"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongmao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064426059","display_name":"Heyang Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heyang Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016567570","display_name":"Hanzhao Li","orcid":"https://orcid.org/0009-0005-3215-7517"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanzhao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037905363","display_name":"Tingwei Guo","orcid":"https://orcid.org/0000-0003-4089-1867"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tingwei Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029228290","display_name":"Ruixiong Zhang","orcid":"https://orcid.org/0000-0002-8597-8969"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruixiong Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100532094","display_name":"Caixia Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Caixia Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9159,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.94838087,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4444","last_page":"4448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9650999903678894,"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":0.9650999903678894,"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":0.9416000247001648,"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/computer-science","display_name":"Computer science","score":0.6539297699928284},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5874987244606018},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5694949626922607},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.5690385103225708},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.48748326301574707},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4577125906944275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42561620473861694},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.25204914808273315},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17448967695236206},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1529512107372284},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.13786786794662476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08154752850532532}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6539297699928284},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5874987244606018},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5694949626922607},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.5690385103225708},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.48748326301574707},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4577125906944275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42561620473861694},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.25204914808273315},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17448967695236206},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1529512107372284},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.13786786794662476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08154752850532532},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-391","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-391","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/W3207249698","https://openalex.org/W1528909574","https://openalex.org/W2122830402","https://openalex.org/W4386953238","https://openalex.org/W2552590214","https://openalex.org/W3207038517","https://openalex.org/W2921857201","https://openalex.org/W169038075","https://openalex.org/W2069501481","https://openalex.org/W3207340675"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
