{"id":"https://openalex.org/W4224927653","doi":"https://doi.org/10.1109/icassp43922.2022.9746812","title":"HiFi-SVC: Fast High Fidelity Cross-Domain Singing Voice Conversion","display_name":"HiFi-SVC: Fast High Fidelity Cross-Domain Singing Voice Conversion","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224927653","doi":"https://doi.org/10.1109/icassp43922.2022.9746812"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746812","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5057416557","display_name":"Yong Zhou","orcid":"https://orcid.org/0000-0002-3319-9795"},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yong Zhou","raw_affiliation_strings":["iQIYI Inc,China","iQIYI Inc, China"],"affiliations":[{"raw_affiliation_string":"iQIYI Inc,China","institution_ids":["https://openalex.org/I4210115040"]},{"raw_affiliation_string":"iQIYI Inc, China","institution_ids":["https://openalex.org/I4210115040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080066452","display_name":"Xiangju Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115040","display_name":"iQIYI (China)","ror":"https://ror.org/026xvz038","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210115040"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangju Lu","raw_affiliation_strings":["iQIYI Inc,China","iQIYI Inc, China"],"affiliations":[{"raw_affiliation_string":"iQIYI Inc,China","institution_ids":["https://openalex.org/I4210115040"]},{"raw_affiliation_string":"iQIYI Inc, China","institution_ids":["https://openalex.org/I4210115040"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057416557"],"corresponding_institution_ids":["https://openalex.org/I4210115040"],"apc_list":null,"apc_paid":null,"fwci":0.9349,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7550097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6667","last_page":"6671"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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":0.9984999895095825,"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/singing","display_name":"Singing","score":0.7887147665023804},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7557857036590576},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7205625772476196},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6073082089424133},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5930346846580505},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.5382236242294312},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.47650590538978577},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4277645945549011},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.34925609827041626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2479061484336853},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24185100197792053},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10476687550544739},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08056065440177917},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06981489062309265}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7887147665023804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557857036590576},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7205625772476196},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6073082089424133},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5930346846580505},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.5382236242294312},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.47650590538978577},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4277645945549011},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.34925609827041626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2479061484336853},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24185100197792053},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10476687550544739},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08056065440177917},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06981489062309265},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746812","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746812","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":39,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2067709094","https://openalex.org/W2137637927","https://openalex.org/W2471520273","https://openalex.org/W2518172956","https://openalex.org/W2726515241","https://openalex.org/W2734498959","https://openalex.org/W2774848319","https://openalex.org/W2808631503","https://openalex.org/W2937579788","https://openalex.org/W2962866891","https://openalex.org/W2972394484","https://openalex.org/W2972659941","https://openalex.org/W2998572311","https://openalex.org/W3024869864","https://openalex.org/W3083423753","https://openalex.org/W3092028330","https://openalex.org/W3094843121","https://openalex.org/W3095936335","https://openalex.org/W3095948607","https://openalex.org/W3097777922","https://openalex.org/W3123097577","https://openalex.org/W3162512456","https://openalex.org/W3163475957","https://openalex.org/W3163568691","https://openalex.org/W3165478005","https://openalex.org/W3167533889","https://openalex.org/W3170751106","https://openalex.org/W6629717138","https://openalex.org/W6740674931","https://openalex.org/W6746801104","https://openalex.org/W6761580982","https://openalex.org/W6777337586","https://openalex.org/W6782760101","https://openalex.org/W6783867762","https://openalex.org/W6784504775","https://openalex.org/W6784691655","https://openalex.org/W6785058572","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4236436342","https://openalex.org/W4372142139","https://openalex.org/W4312790814","https://openalex.org/W3205154814","https://openalex.org/W4205738014","https://openalex.org/W2468514837","https://openalex.org/W4224927653","https://openalex.org/W4206285077","https://openalex.org/W3082910224","https://openalex.org/W4308731235"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"HiFi-SVC,":[3],"a":[4,25,63],"small":[5],"cross-domain":[6],"singing":[7,16,40],"voice":[8,44],"conversion":[9,69],"model":[10],"for":[11,28,67],"generating":[12],"high-fidelity":[13],"22.05":[14],"kHz":[15],"voices.":[17],"Building":[18],"on":[19,46],"state-of-the-art":[20],"neural":[21],"vocoder":[22],"HiFi-GAN":[23],"and":[24],"convolution-based":[26],"module":[27],"modeling":[29],"F0,":[30],"HiFi-SVC":[31],"can":[32],"be":[33],"trained":[34],"end-to-end":[35],"with":[36],"either":[37],"speech":[38],"or":[39],"data,":[41],"achieving":[42],"better":[43],"similarity":[45],"two":[47],"of":[48,58],"the":[49],"datasets":[50],"than":[51],"FastSVC":[52],"while":[53],"using":[54],"slightly":[55],"smaller":[56],"number":[57],"parameters.":[59],"We":[60],"also":[61],"propose":[62],"pitch":[64],"adjustment":[65],"method":[66],"improving":[68],"quality.":[70]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}