{"id":"https://openalex.org/W3015611309","doi":"https://doi.org/10.1109/icassp40776.2020.9053202","title":"WaveFFJORD: FFJORD-Based Vocoder for Statistical Parametric Speech Synthesis","display_name":"WaveFFJORD: FFJORD-Based Vocoder for Statistical Parametric Speech Synthesis","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015611309","doi":"https://doi.org/10.1109/icassp40776.2020.9053202","mag":"3015611309"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5082235402","display_name":"Ning-Qian Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ning-Qian Wu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082235402"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.3256,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84472553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7214","last_page":"7218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9991999864578247,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.8960974216461182},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7596620321273804},{"id":"https://openalex.org/keywords/invertible-matrix","display_name":"Invertible matrix","score":0.6653825044631958},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6080496311187744},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.608012318611145},{"id":"https://openalex.org/keywords/jacobian-matrix-and-determinant","display_name":"Jacobian matrix and determinant","score":0.5814871191978455},{"id":"https://openalex.org/keywords/ordinary-differential-equation","display_name":"Ordinary differential equation","score":0.5323550701141357},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.49814867973327637},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48221099376678467},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3882739245891571},{"id":"https://openalex.org/keywords/differential-equation","display_name":"Differential equation","score":0.22560667991638184},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.20271173119544983},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1820569932460785}],"concepts":[{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.8960974216461182},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7596620321273804},{"id":"https://openalex.org/C96442724","wikidata":"https://www.wikidata.org/wiki/Q242188","display_name":"Invertible matrix","level":2,"score":0.6653825044631958},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6080496311187744},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.608012318611145},{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.5814871191978455},{"id":"https://openalex.org/C51544822","wikidata":"https://www.wikidata.org/wiki/Q465274","display_name":"Ordinary differential equation","level":3,"score":0.5323550701141357},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.49814867973327637},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48221099376678467},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3882739245891571},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.22560667991638184},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.20271173119544983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1820569932460785},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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/icassp40776.2020.9053202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053202","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1583912456","https://openalex.org/W1990457366","https://openalex.org/W2049686551","https://openalex.org/W2102003408","https://openalex.org/W2111284386","https://openalex.org/W2334591577","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2749651610","https://openalex.org/W2769810959","https://openalex.org/W2947196194","https://openalex.org/W2962695743","https://openalex.org/W2962882868","https://openalex.org/W2963139417","https://openalex.org/W2963300588","https://openalex.org/W2963641970","https://openalex.org/W2963755523","https://openalex.org/W2963782041","https://openalex.org/W2963975282","https://openalex.org/W2964020555","https://openalex.org/W2964307104","https://openalex.org/W4288337064","https://openalex.org/W4289305009","https://openalex.org/W4289761690","https://openalex.org/W4294619240","https://openalex.org/W4297798428","https://openalex.org/W4298580827","https://openalex.org/W6635084905","https://openalex.org/W6635231448","https://openalex.org/W6714644935","https://openalex.org/W6732429163","https://openalex.org/W6748409065","https://openalex.org/W6752307458","https://openalex.org/W6752910514","https://openalex.org/W6753855596","https://openalex.org/W6755056417","https://openalex.org/W6755592152","https://openalex.org/W6756159577"],"related_works":["https://openalex.org/W2371448224","https://openalex.org/W3134495997","https://openalex.org/W2363680170","https://openalex.org/W2376428685","https://openalex.org/W4256082577","https://openalex.org/W625783435","https://openalex.org/W2048742619","https://openalex.org/W2384641672","https://openalex.org/W2742179975","https://openalex.org/W162626055"],"abstract_inverted_index":{"Free-form":[0],"Jacobian":[1],"of":[2,98],"Reversible":[3],"Dynamics(FFJORD)":[4],"is":[5],"a":[6,26,67],"flowbased":[7],"invertible":[8],"generative":[9],"model":[10,69],"defined":[11],"by":[12,18,37,48,93],"ordinary":[13],"differential":[14],"equations":[15],"(ODE).":[16],"Inspired":[17],"WaveGlow,":[19],"in":[20],"this":[21],"paper,":[22],"we":[23],"propose":[24],"WaveFFJORD,":[25],"neural":[27],"vocoder":[28],"that":[29,63],"can":[30,43,65],"synthesize":[31],"speech":[32,45,76],"waveforms":[33,46],"from":[34],"acoustic":[35],"features,":[36],"combining":[38],"FFJORD":[39],"and":[40,74,91],"WaveNet.":[41],"WaveFFJORD":[42,64],"generate":[44],"directly":[47],"the":[49,54,81,88,95,99],"blackbox":[50],"ODE":[51,82,100],"solvers,":[52],"without":[53],"need":[55],"for":[56],"autoregressive":[57],"structures.":[58],"Our":[59],"experimental":[60],"results":[61],"show":[62],"achieve":[66],"smaller":[68],"size,":[70],"lower":[71],"memory":[72],"cost,":[73],"better":[75],"quality":[77,92],"than":[78],"WaveGlow.":[79],"Besides,":[80],"framework":[83],"allows":[84],"users":[85],"to":[86],"control":[87],"generation":[89],"speed":[90],"setting":[94],"error":[96],"tolerance":[97],"solvers.":[101]},"counts_by_year":[{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
