{"id":"https://openalex.org/W4372262501","doi":"https://doi.org/10.1109/icassp49357.2023.10095298","title":"Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocoder","display_name":"Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocoder","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372262501","doi":"https://doi.org/10.1109/icassp49357.2023.10095298"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5066881979","display_name":"Reo Yoneyama","orcid":"https://orcid.org/0000-0001-9686-4783"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Reo Yoneyama","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003177601","display_name":"Yi-Chiao Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":["Meta Reality Labs Research,USA","Meta Reality Labs Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs Research,USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Meta Reality Labs Research, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006808971","display_name":"Tomoki Toda","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.9969000220298767,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7965015172958374},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5053640007972717},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3672095537185669}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7965015172958374},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5053640007972717},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3672095537185669},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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":32,"referenced_works":["https://openalex.org/W2020883660","https://openalex.org/W2029434926","https://openalex.org/W2109189270","https://openalex.org/W2150418026","https://openalex.org/W2164764235","https://openalex.org/W2471520273","https://openalex.org/W2593414223","https://openalex.org/W2963175743","https://openalex.org/W2970006822","https://openalex.org/W2990440871","https://openalex.org/W3041738652","https://openalex.org/W3045000780","https://openalex.org/W3092028330","https://openalex.org/W3096429957","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3130168980","https://openalex.org/W3161236344","https://openalex.org/W3162536450","https://openalex.org/W3169905056","https://openalex.org/W3196969505","https://openalex.org/W3197273793","https://openalex.org/W3197385343","https://openalex.org/W3207340675","https://openalex.org/W4224612669","https://openalex.org/W4280575909","https://openalex.org/W4320013936","https://openalex.org/W6767111847","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6796464841"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2368779261","https://openalex.org/W2778699561","https://openalex.org/W2113644136","https://openalex.org/W2367330275","https://openalex.org/W2156119704"],"abstract_inverted_index":{"Our":[0],"previous":[1],"work,":[2],"the":[3,15,20,35,46,56,61,79,87,99,127,130],"unified":[4],"source-filter":[5,80],"GAN":[6,109],"(uSFGAN)":[7],"vocoder,":[8,76,129],"introduced":[9],"a":[10,69,92,111,122],"novel":[11],"architecture":[12],"based":[13],"on":[14,91,110,121],"source-":[16],"filter":[17],"theory":[18,81],"into":[19,82],"parallel":[21],"waveform":[22],"generative":[23],"adversarial":[24],"network":[25,90],"to":[26,55,98],"achieve":[27],"high":[28,36,42],"voice":[29,52,113,116],"quality":[30,117],"and":[31,71,107,118,140],"pitch":[32,62],"controllability.":[33],"However,":[34],"temporal":[37],"resolution":[38],"inputs":[39],"result":[40],"in":[41,115,137],"computation":[43],"costs.":[44],"Although":[45],"HiFi-GAN":[47,83,106],"vocoder":[48],"achieves":[49],"fast":[50,70],"high-fidelity":[51,74],"generation":[53,114],"thanks":[54],"efficient":[57],"upsampling-based":[58],"generator":[59],"architecture,":[60],"controllability":[63],"is":[64],"severely":[65],"limited.":[66],"To":[67],"realize":[68],"pitch-":[72],"controllable":[73],"neural":[75],"we":[77],"introduce":[78],"by":[84],"hierarchically":[85],"conditioning":[86],"resonance":[88],"filtering":[89],"well-estimated":[93],"source":[94],"excitation":[95],"information.":[96],"According":[97],"experimental":[100],"results,":[101],"our":[102],"proposed":[103,131],"method":[104,132],"outperforms":[105],"uSF-":[108],"singing":[112],"synthesis":[119],"speed":[120],"single":[123],"CPU.":[124],"Furthermore,":[125],"unlike":[126],"uSFGAN":[128],"can":[133],"be":[134],"easily":[135],"adopted/integrated":[136],"real-time":[138],"applications":[139],"end-to-end":[141],"systems.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}