{"id":"https://openalex.org/W4392902768","doi":"https://doi.org/10.1109/icassp48485.2024.10448502","title":"PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model","display_name":"PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902768","doi":"https://doi.org/10.1109/icassp48485.2024.10448502"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5086910479","display_name":"Yukiya Hono","orcid":"https://orcid.org/0000-0003-1245-8791"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukiya Hono","raw_affiliation_strings":["Nagoya Institute of Technology,Nagoya,Japan","Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067594810","display_name":"Kei Hashimoto","orcid":"https://orcid.org/0000-0003-2081-0396"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Hashimoto","raw_affiliation_strings":["Nagoya Institute of Technology,Nagoya,Japan","Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":["Nagoya Institute of Technology,Nagoya,Japan","Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Nagoya Institute of Technology,Nagoya,Japan","Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology,Nagoya,Japan","institution_ids":["https://openalex.org/I197274945"]},{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12782","last_page":"12786"},"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":0.9994999766349792,"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":0.9962000250816345,"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/waveform","display_name":"Waveform","score":0.7441951036453247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7294384837150574},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.514279305934906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5051446557044983},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44511377811431885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23094838857650757},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.08703139424324036},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07147759199142456}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7441951036453247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7294384837150574},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.514279305934906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5051446557044983},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44511377811431885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23094838857650757},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.08703139424324036},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07147759199142456}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448502","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2769810959","https://openalex.org/W2963091184","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W3015338123","https://openalex.org/W3082910224","https://openalex.org/W3162075194","https://openalex.org/W3187128306","https://openalex.org/W3190244907","https://openalex.org/W3204728450","https://openalex.org/W4224931676","https://openalex.org/W4225566824","https://openalex.org/W4298580827","https://openalex.org/W4312933868","https://openalex.org/W4372262501","https://openalex.org/W4372262701","https://openalex.org/W4382296240","https://openalex.org/W4395961138","https://openalex.org/W6732429163","https://openalex.org/W6748409065","https://openalex.org/W6765775151","https://openalex.org/W6767111847","https://openalex.org/W6771024825","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783382068","https://openalex.org/W6783867762","https://openalex.org/W6786375611","https://openalex.org/W6795288823","https://openalex.org/W6797906067","https://openalex.org/W6840257003"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W1974895211","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2176409448","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,8,49,63],"neural":[4,24,38,66,80,125],"vocoder":[5],"based":[6,40],"on":[7,41],"denoising":[9],"diffusion":[10],"probabilistic":[11],"model":[12,92,113],"(DDPM)":[13],"incorporating":[14,104],"explicit":[15,105],"periodic":[16,98,106],"signals":[17],"as":[18,29,57],"auxiliary":[19],"conditioning":[20],"signals.":[21,107],"Recently,":[22],"DDPM-based":[23,79,124],"vocoders":[25,39,67,81],"have":[26,43],"gained":[27],"prominence":[28],"non-autoregressive":[30],"models":[31],"that":[32,111],"can":[33],"generate":[34,69,84],"high-quality":[35],"waveforms.":[36],"The":[37],"DDPM":[42],"the":[44,97],"advantage":[45],"of":[46,100],"training":[47],"with":[48,73],"simple":[50],"time-domain":[51],"loss.":[52],"In":[53],"practical":[54],"applications,":[55],"such":[56,88],"singing":[58],"voice":[59],"synthesis,":[60],"there":[61],"is":[62],"demand":[64],"for":[65],"to":[68,83,94],"high-fidelity":[70],"speech":[71,85,101],"waveforms":[72,86,102],"flexible":[74],"pitch":[75,120],"control.":[76],"However,":[77],"conventional":[78,123],"struggle":[82],"under":[87],"conditions.":[89],"Our":[90],"proposed":[91],"aims":[93],"accurately":[95],"capture":[96],"structure":[99],"by":[103],"Experimental":[108],"results":[109],"show":[110],"our":[112],"improves":[114],"sound":[115],"quality":[116],"and":[117],"provides":[118],"better":[119],"control":[121],"than":[122],"vocoders.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}