{"id":"https://openalex.org/W4382296240","doi":"https://doi.org/10.1109/taslp.2023.3275032","title":"Harmonic-Net: Fundamental Frequency and Speech Rate Controllable Fast Neural Vocoder","display_name":"Harmonic-Net: Fundamental Frequency and Speech Rate Controllable Fast Neural Vocoder","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4382296240","doi":"https://doi.org/10.1109/taslp.2023.3275032"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3275032","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3275032","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10122591.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10122591.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082668383","display_name":"Keisuke Matsubara","orcid":"https://orcid.org/0000-0002-2935-668X"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Matsubara","raw_affiliation_strings":["Graduate School of System Informatics, Kobe University, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2935-668X","affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022943637","display_name":"Takuma Okamoto","orcid":"https://orcid.org/0000-0001-9913-4647"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9913-4647","affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057295313","display_name":"Ryoichi Takashima","orcid":"https://orcid.org/0000-0002-9808-0250"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoichi Takashima","raw_affiliation_strings":["Graduate School of System Informatics, Kobe University, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9808-0250","affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009283470","display_name":"Tetsuya Takiguchi","orcid":"https://orcid.org/0000-0001-5005-7679"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Takiguchi","raw_affiliation_strings":["Graduate School of System Informatics, Kobe University, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5005-7679","affiliations":[{"raw_affiliation_string":"Graduate School of System Informatics, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7449,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86829877,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"1902","last_page":"1915"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.998199999332428,"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/upsampling","display_name":"Upsampling","score":0.6508405208587646},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5020959377288818},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4673369824886322},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.440257728099823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.41969534754753113},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.37531644105911255},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.361797571182251},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3546292781829834},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.32341456413269043},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.3227275609970093},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.30410143733024597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25405165553092957},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.21657133102416992},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.18348243832588196},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16687539219856262},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10216465592384338}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.6508405208587646},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5020959377288818},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4673369824886322},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.440257728099823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.41969534754753113},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37531644105911255},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.361797571182251},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3546292781829834},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.32341456413269043},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.3227275609970093},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.30410143733024597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25405165553092957},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.21657133102416992},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.18348243832588196},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16687539219856262},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10216465592384338},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3275032","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3275032","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10122591.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2023.3275032","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3275032","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/9970249/10122591.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382296240.pdf","grobid_xml":"https://content.openalex.org/works/W4382296240.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1541019354","https://openalex.org/W1563460361","https://openalex.org/W2012086895","https://openalex.org/W2030149476","https://openalex.org/W2049686551","https://openalex.org/W2111284386","https://openalex.org/W2164764235","https://openalex.org/W2168510624","https://openalex.org/W2428180336","https://openalex.org/W2471520273","https://openalex.org/W2478884216","https://openalex.org/W2519648275","https://openalex.org/W2576309025","https://openalex.org/W2747070883","https://openalex.org/W2749651610","https://openalex.org/W2786868129","https://openalex.org/W2797310469","https://openalex.org/W2803229097","https://openalex.org/W2937829825","https://openalex.org/W2951310434","https://openalex.org/W2954386831","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2990440871","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3041738652","https://openalex.org/W3045000780","https://openalex.org/W3081800019","https://openalex.org/W3094843121","https://openalex.org/W3096429957","https://openalex.org/W3097003111","https://openalex.org/W3104557543","https://openalex.org/W3130168980","https://openalex.org/W3144035034","https://openalex.org/W3159302906","https://openalex.org/W3162075194","https://openalex.org/W3165891254","https://openalex.org/W3196468212","https://openalex.org/W3197273793","https://openalex.org/W3197385343","https://openalex.org/W3198011653","https://openalex.org/W3198843334","https://openalex.org/W3204728450","https://openalex.org/W4210287297","https://openalex.org/W4210633887","https://openalex.org/W4221055745","https://openalex.org/W4221152438","https://openalex.org/W4226421894","https://openalex.org/W6687506355","https://openalex.org/W6748409065","https://openalex.org/W6753855596","https://openalex.org/W6756197946","https://openalex.org/W6763832098","https://openalex.org/W6767111847","https://openalex.org/W6771763809","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6802838302"],"related_works":["https://openalex.org/W2062399876","https://openalex.org/W2607795551","https://openalex.org/W3155117723","https://openalex.org/W1991429770","https://openalex.org/W1983892167","https://openalex.org/W2281134365","https://openalex.org/W4310746709","https://openalex.org/W4385574037","https://openalex.org/W4386075645","https://openalex.org/W4306309518"],"abstract_inverted_index":{"There":[0],"is":[1,56,81],"a":[2,57],"need":[3],"to":[4,72,104,128,135,178],"improve":[5],"the":[6,21,50,61,82,98,114,140,151,171],"synthesis":[7,138,168,186],"quality":[8,187],"of":[9,23,122,156],"HiFi-GAN-based":[10],"real-time":[11],"neural":[12],"speech":[13,33],"waveform":[14],"generative":[15],"models":[16],"on":[17,97],"CPUs":[18],"while":[19],"preserving":[20],"controllability":[22],"fundamental":[24],"frequency":[25],"(":[26],"<inline-formula":[27,73,100,109,129,143,179,195],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[28,74,101,110,130,144,180,196],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[29,75,102,111,131,145,181,197],"notation=\"LaTeX\">$f_{\\mathrm{o}}$</tex-math></inline-formula>":[30,76,103,112,132,146,182,198],")":[31],"and":[32,42,125,142,149,166,200],"rate":[34],"(SR).":[35],"For":[36],"this":[37],"purpose,":[38],"we":[39],"propose":[40],"Harmonic-Net":[41],"Harmonic-Net+,":[43],"which":[44,89],"introduce":[45],"two":[46],"extended":[47],"functions":[48],"into":[49],"HiFi-GAN":[51,116],"generator.":[52,117],"The":[53,78,118,154],"first":[54],"extension":[55,80],"downsampling":[58],"network,":[59,64],"named":[60],"excitation":[62,69,123],"signal":[63],"that":[65,170],"hierarchically":[66],"receives":[67],"multi-channel":[68],"signals":[70,124],"corresponding":[71,127,177],".":[77],"second":[79],"layerwise":[83],"pitch-dependent":[84],"dilated":[85],"convolutional":[86],"network":[87],"(LW-PDCNN),":[88],"can":[90,183],"flexibly":[91],"change":[92],"its":[93],"receptive":[94],"fields":[95],"depending":[96],"input":[99,121],"handle":[105],"large":[106],"fluctuations":[107],"in":[108,191],"for":[113,139,150,158],"upsampling-based":[115],"proposed":[119,172],"explicit":[120],"LW-PDCNNs":[126],"are":[133],"expected":[134],"realize":[136],"high-quality":[137],"normal":[141],"-conversion":[147],"conditions":[148],"SR-conversion":[152],"condition.":[153],"results":[155],"experiments":[157],"unseen":[159],"speaker":[160],"synthesis,":[161,165],"full-band":[162],"singing":[163],"voice":[164],"text-to-speech":[167],"show":[169],"method":[173],"with":[174],"harmonic":[175],"waves":[176],"achieve":[184],"higher":[185],"than":[188],"conventional":[189],"methods":[190],"all":[192],"(i.e.,":[193],"normal,":[194],"-conversion,":[199],"SR-conversion)":[201],"conditions.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}