{"id":"https://openalex.org/W3197385343","doi":"https://doi.org/10.21437/interspeech.2021-517","title":"Unified Source-Filter GAN: Unified Source-Filter Network Based On Factorization of Quasi-Periodic Parallel WaveGAN","display_name":"Unified Source-Filter GAN: Unified Source-Filter Network Based On Factorization of Quasi-Periodic Parallel WaveGAN","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197385343","doi":"https://doi.org/10.21437/interspeech.2021-517","mag":"3197385343"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-517","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5052707306","display_name":"Reo Yoneyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reo Yoneyama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037001032","display_name":"Yi-Chiao Wu","orcid":"https://orcid.org/0000-0003-4390-1354"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi-Chiao Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2187","last_page":"2191"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9980999827384949,"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":0.9911999702453613,"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/computer-science","display_name":"Computer science","score":0.7783092260360718},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6139135360717773},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6040068864822388},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5568690896034241},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.443612664937973},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3993101119995117},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3448796570301056},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3117777109146118},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10186803340911865}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783092260360718},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6139135360717773},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6040068864822388},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5568690896034241},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.443612664937973},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3993101119995117},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3448796570301056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3117777109146118},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10186803340911865},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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":1,"locations":[{"id":"doi:10.21437/interspeech.2021-517","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2079194684","https://openalex.org/W2617269004","https://openalex.org/W35292311","https://openalex.org/W2803166627","https://openalex.org/W2046073792","https://openalex.org/W1748856376","https://openalex.org/W2099204336","https://openalex.org/W153239700","https://openalex.org/W2067459736","https://openalex.org/W2105635394"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,10,16,63,68,74,83,94,106],"unified":[3,42],"approach":[4],"to":[5,33,104],"data-driven":[6],"source-filter":[7,31,43],"modeling":[8],"using":[9],"single":[11,64],"neural":[12,17,59,65,89,130],"network":[13,40,72,79],"for":[14],"developing":[15],"vocoder":[18],"capable":[19],"of":[20,29,57,115],"generating":[21],"high-quality":[22],"synthetic":[23],"speech":[24,139],"waveforms":[25],"while":[26,111],"retaining":[27],"flexibility":[28],"the":[30,58,101,113,118],"model":[32],"control":[34],"their":[35],"voice":[36],"characteristics.":[37],"Our":[38],"proposed":[39],"called":[41],"generative":[44],"adversarial":[45],"networks":[46],"(uSFGAN)":[47],"is":[48,97],"developed":[49],"by":[50,80,88],"factorizing":[51],"quasi-periodic":[52],"parallel":[53],"WaveGAN":[54],"(QPPWG),":[55],"one":[56],"vocoders":[60],"based":[61],"on":[62],"network,":[66],"into":[67],"source":[69,90,108,119],"excitation":[70,109],"generation":[71],"and":[73,135,141],"vocal":[75],"tract":[76],"resonance":[77],"filtering":[78],"additionally":[81,98],"implementing":[82],"regularization":[84],"loss.":[85],"Moreover,":[86],"inspired":[87],"filter":[91,120],"(NSF),":[92],"only":[93],"sinusoidal":[95],"waveform":[96,110],"used":[99],"as":[100,133],"simplest":[102],"clue":[103],"generate":[105],"periodic":[107],"minimizing":[112],"effect":[114],"approximations":[116],"in":[117,137],"model.":[121],"The":[122],"experimental":[123],"results":[124],"demonstrate":[125],"that":[126],"uSFGAN":[127],"outperforms":[128],"conventional":[129],"vocoders,":[131],"such":[132],"QPPWG":[134],"NSF":[136],"both":[138],"quality":[140],"pitch":[142],"controllability.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}