{"id":"https://openalex.org/W4386608861","doi":"https://doi.org/10.1109/taslp.2023.3313410","title":"High-Fidelity and Pitch-Controllable Neural Vocoder Based on Unified Source-Filter Networks","display_name":"High-Fidelity and Pitch-Controllable Neural Vocoder Based on Unified Source-Filter Networks","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386608861","doi":"https://doi.org/10.1109/taslp.2023.3313410"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3313410","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313410","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10246854.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10246854.pdf","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":["Graduate School of Informatics, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9686-4783","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"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":"Yi-Chiao Wu","raw_affiliation_strings":["Graduate School of Informatics, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0003-4390-1354","affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"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":["Information Technology Center, Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8146-1279","affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":1.3918,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82481517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"3717","last_page":"3729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.5608702301979065},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4843669831752777},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.46908846497535706},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45862406492233276},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4209633469581604},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3939661979675293},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3939545750617981},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3533569574356079},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2218320071697235},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.09749573469161987},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08515763282775879}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5608702301979065},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4843669831752777},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.46908846497535706},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45862406492233276},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4209633469581604},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3939661979675293},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3939545750617981},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3533569574356079},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2218320071697235},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.09749573469161987},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08515763282775879},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3313410","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313410","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10246854.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2023.3313410","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3313410","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10246854.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7893352204","display_name":null,"funder_award_id":"JP21H05054","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8892501299","display_name":null,"funder_award_id":"JPMJCR19A3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386608861.pdf","grobid_xml":"https://content.openalex.org/works/W4386608861.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1969526148","https://openalex.org/W2012086895","https://openalex.org/W2049686551","https://openalex.org/W2109189270","https://openalex.org/W2129082420","https://openalex.org/W2150418026","https://openalex.org/W2164764235","https://openalex.org/W2471520273","https://openalex.org/W2519648275","https://openalex.org/W2747070883","https://openalex.org/W2748379347","https://openalex.org/W2749651610","https://openalex.org/W2962898107","https://openalex.org/W2963091184","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2972309641","https://openalex.org/W2972333964","https://openalex.org/W2972597685","https://openalex.org/W2973115941","https://openalex.org/W2975414524","https://openalex.org/W2990440871","https://openalex.org/W2998572311","https://openalex.org/W3015338123","https://openalex.org/W3041738652","https://openalex.org/W3045000780","https://openalex.org/W3095787156","https://openalex.org/W3096429957","https://openalex.org/W3097828251","https://openalex.org/W3130168980","https://openalex.org/W3144035034","https://openalex.org/W3160326269","https://openalex.org/W3161236344","https://openalex.org/W3162536450","https://openalex.org/W3196969505","https://openalex.org/W3197385343","https://openalex.org/W3198234802","https://openalex.org/W3202871751","https://openalex.org/W4245284779","https://openalex.org/W4280575909","https://openalex.org/W4285112711","https://openalex.org/W6631190155","https://openalex.org/W6748326514","https://openalex.org/W6748409065","https://openalex.org/W6753855596","https://openalex.org/W6767111847","https://openalex.org/W6767164110","https://openalex.org/W6771024825","https://openalex.org/W6772349387","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6802169104","https://openalex.org/W6802838302","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W2504004674","https://openalex.org/W1987679298","https://openalex.org/W2963177394","https://openalex.org/W4313359513","https://openalex.org/W2498744856","https://openalex.org/W4390482104","https://openalex.org/W322408318","https://openalex.org/W149041114","https://openalex.org/W1965815883","https://openalex.org/W763418848"],"abstract_inverted_index":{"We":[0],"introduce":[1],"unified":[2,45],"source-filter":[3,19,29,139],"generative":[4,10],"adversarial":[5],"networks":[6],"(uSFGAN),":[7],"a":[8,22],"waveform":[9],"model":[11],"conditioned":[12],"on":[13],"acoustic":[14],"features,":[15],"which":[16,32],"represents":[17],"the":[18,26,49,63,74,93,97,107,115,126,134,142,155],"architecture":[20],"in":[21,31,106,114,150],"generator":[23],"network.":[24],"Unlike":[25],"previous":[27],"neural-based":[28],"models":[30],"parametric":[33],"signal":[34],"process":[35],"modules":[36],"are":[37,70,90,162],"combined":[38],"with":[39],"neural":[40],"networks,":[41],"our":[42,165],"approach":[43],"enables":[44],"optimization":[46],"of":[47,157],"both":[48],"source":[50,75,82],"excitation":[51,76,83],"generation":[52,77],"and":[53,87,92,111,133],"resonance":[54],"filtering":[55],"parts":[56],"to":[57,72,79,104],"achieve":[58],"higher":[59],"sound":[60,102],"quality.":[61],"In":[62],"uSFGAN":[64,99],"framework,":[65],"several":[66],"specific":[67],"regularization":[68],"losses":[69],"proposed":[71,98],"enable":[73],"part":[78],"output":[80],"reasonable":[81],"signals.":[84],"Both":[85],"objective":[86],"subjective":[88],"experiments":[89],"conducted,":[91],"results":[94,156],"demonstrate":[95],"that":[96,125],"achieves":[100],"comparable":[101],"quality":[103],"HiFi-GAN":[105],"speech":[108],"reconstruction":[109],"task":[110],"outperforms":[112],"WORLD":[113],"<inline-formula":[116,127,146],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[117,128,147,170],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[118,129,148],"notation=\"LaTeX\">$\\text{F}_{0}$</tex-math></inline-formula>":[119,130,149],"transformation":[120],"task.":[121],"Moreover,":[122],"we":[123],"argue":[124],"-driven":[131],"mechanism":[132],"inductive":[135],"bias":[136],"obtained":[137],"by":[138,154],"modeling":[140],"improve":[141],"robustness":[143],"against":[144],"unseen":[145],"training":[151],"as":[152],"shown":[153],"experimental":[158],"evaluations.":[159],"Audio":[160],"samples":[161],"available":[163],"at":[164,168],"demo":[166],"site":[167],"<uri":[169],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://chomeyama.github.io/PitchControllableNeuralVocoder-Demo/</uri>":[171],".":[172]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}