{"id":"https://openalex.org/W4206397897","doi":"https://doi.org/10.1109/taslp.2022.3140480","title":"NeuralDPS: Neural Deterministic Plus Stochastic Model With Multiband Excitation for Noise-Controllable Waveform Generation","display_name":"NeuralDPS: Neural Deterministic Plus Stochastic Model With Multiband Excitation for Noise-Controllable Waveform Generation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4206397897","doi":"https://doi.org/10.1109/taslp.2022.3140480"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3140480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3140480","pdf_url":null,"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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.02678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071038184","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0003-1490-6973"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Wang","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1490-6973","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073918837","display_name":"Ruibo Fu","orcid":"https://orcid.org/0000-0001-9598-1881"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibo Fu","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9598-1881","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2422-4618","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9344-6428","affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000843913","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2828,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44741941,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"30","issue":null,"first_page":"865","last_page":"878"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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/T10320","display_name":"Neural Networks and Applications","score":0.9968000054359436,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9945999979972839,"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":0.7806241512298584},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.57951819896698},{"id":"https://openalex.org/keywords/excitation","display_name":"Excitation","score":0.579108476638794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4274592697620392},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41534343361854553},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.4069305658340454},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.3993009924888611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17259934544563293},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11263924837112427}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7806241512298584},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.57951819896698},{"id":"https://openalex.org/C83581075","wikidata":"https://www.wikidata.org/wiki/Q1361503","display_name":"Excitation","level":2,"score":0.579108476638794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4274592697620392},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41534343361854553},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4069305658340454},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3993009924888611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17259934544563293},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11263924837112427},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2022.3140480","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3140480","pdf_url":null,"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"},{"id":"pmh:oai:arXiv.org:2203.02678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.02678","pdf_url":"https://arxiv.org/pdf/2203.02678","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.02678","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.02678","pdf_url":"https://arxiv.org/pdf/2203.02678","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G5381013183","display_name":null,"funder_award_id":"61831022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7264488544","display_name":"\u60c5\u611f\u8bed\u97f3\u97f3\u8272\u5206\u6790\u53ca\u8865\u507f\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61771472","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7853071381","display_name":null,"funder_award_id":"62101553","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8374701036","display_name":null,"funder_award_id":"61901473","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W95152782","https://openalex.org/W138714085","https://openalex.org/W1496971974","https://openalex.org/W1522301498","https://openalex.org/W1601809792","https://openalex.org/W2052384514","https://openalex.org/W2064675550","https://openalex.org/W2066999516","https://openalex.org/W2093824445","https://openalex.org/W2098372067","https://openalex.org/W2109189270","https://openalex.org/W2112094107","https://openalex.org/W2117946322","https://openalex.org/W2129082420","https://openalex.org/W2129142580","https://openalex.org/W2146348023","https://openalex.org/W2148371116","https://openalex.org/W2172065531","https://openalex.org/W2302255633","https://openalex.org/W2471520273","https://openalex.org/W2478884216","https://openalex.org/W2515336442","https://openalex.org/W2519091744","https://openalex.org/W2576309025","https://openalex.org/W2584032004","https://openalex.org/W2616492649","https://openalex.org/W2749651610","https://openalex.org/W2803229097","https://openalex.org/W2899771611","https://openalex.org/W2929299742","https://openalex.org/W2951310434","https://openalex.org/W2963091184","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W3015338123","https://openalex.org/W3038172701","https://openalex.org/W3096159803","https://openalex.org/W3104557543","https://openalex.org/W3129651364","https://openalex.org/W3184998487","https://openalex.org/W4235422353","https://openalex.org/W4250648261","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W6603838645","https://openalex.org/W6631190155","https://openalex.org/W6636056872","https://openalex.org/W6694401350","https://openalex.org/W6732429163","https://openalex.org/W6748409065","https://openalex.org/W6756040250","https://openalex.org/W6760385162","https://openalex.org/W6767111847","https://openalex.org/W6779871621","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6843673214","https://openalex.org/W6917585676"],"related_works":["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","https://openalex.org/W4367555392","https://openalex.org/W2538520412","https://openalex.org/W2883092465"],"abstract_inverted_index":{"The":[0,88],"traditional":[1,36],"vocoders":[2,18],"have":[3,19,121,219],"the":[4,16,20,28,35,92,96,101,114,145,163,189,201,230,234,239],"advantages":[5,29],"of":[6,22,30,124,156,167,241],"high":[7,23,53,58],"synthesis":[8,24,59,211],"efficiency,":[9],"strong":[10],"interpretability,":[11],"and":[12,56,61,83,127,143,174,191,237],"speech":[13,54,157,168,236],"editability,":[14],"while":[15],"neural":[17,46,79,85,146],"advantage":[21],"quality.":[25],"To":[26],"combine":[27],"two":[31],"vocoders,":[32],"inspired":[33],"by":[34,91,104],"deterministic":[37,71,125],"plus":[38],"stochastic":[39,75,128],"model,":[40],"this":[41,65,161,225],"paper":[42],"proposes":[43],"a":[44,70,74,78,84,130,138,150,214],"novel":[45],"vocoder":[47,93,183],"named":[48],"NeuralDPS":[49,182],"which":[50,99],"can":[51,169,184,227],"retain":[52],"quality":[55],"acquire":[57],"efficiency":[60,212],"noise":[62,154,231],"controllability.":[63],"Firstly,":[64],"framework":[66],"contains":[67],"four":[68],"modules:":[69],"source":[72,76],"module,":[73,77],"V/UV":[80],"decision":[81],"module":[82],"filter":[86],"module.":[87],"input":[89],"required":[90],"is":[94,134,158,205],"just":[95],"spectral":[97],"parameter,":[98],"avoids":[100],"error":[102],"caused":[103],"estimating":[105],"additional":[106],"parameters,":[107],"such":[108],"as":[109],"F0.":[110],"Secondly,":[111],"to":[112,136,152],"solve":[113],"problem":[115],"that":[116,179,224],"different":[117,122],"frequency":[118],"bands":[119],"may":[120],"proportions":[123],"components":[126,155,232],"components,":[129],"multiband":[131],"excitation":[132,141],"strategy":[133],"used":[135],"generate":[137],"more":[139],"accurate":[140],"signal":[142],"reduce":[144],"filter\u2019s":[147],"burden.":[148],"Thirdly,":[149],"method":[151,226],"control":[153,229],"proposed.":[159],"In":[160],"way,":[162],"signal-to-noise":[164],"ratio":[165],"(SNR)":[166],"be":[170],"adjusted":[171],"easily.":[172],"Objective":[173],"subjective":[175],"experimental":[176],"results":[177],"show":[178],"our":[180],"proposed":[181],"obtain":[185],"similar":[186],"performance":[187],"with":[188],"WaveNet":[190,202],"it":[192],"generates":[193],"waveforms":[194],"at":[195],"least":[196],"280":[197],"times":[198],"faster":[199,208],"than":[200,209],"vocoder.":[203],"It":[204],"also":[206,220],"28%":[207],"WaveGAN\u2019s":[210],"on":[213],"single":[215],"CPU":[216],"core.":[217],"We":[218],"verified":[221],"through":[222],"experiments":[223],"effectively":[228],"in":[233],"predicted":[235],"adjust":[238],"SNR":[240],"speech.":[242]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-01-25T00:00:00"}