{"id":"https://openalex.org/W4280575909","doi":"https://doi.org/10.21437/interspeech.2022-11130","title":"Unified Source-Filter GAN with Harmonic-plus-Noise Source Excitation Generation","display_name":"Unified Source-Filter GAN with Harmonic-plus-Noise Source Excitation Generation","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4280575909","doi":"https://doi.org/10.21437/interspeech.2022-11130"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11130","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11130","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5050687792","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":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"848","last_page":"852"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9966999888420105,"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":0.9962999820709229,"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":0.7147606611251831},{"id":"https://openalex.org/keywords/comb-filter","display_name":"Comb filter","score":0.5913867950439453},{"id":"https://openalex.org/keywords/aperiodic-graph","display_name":"Aperiodic graph","score":0.5797963738441467},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.5572651624679565},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5357306003570557},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5245176553726196},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4529593586921692},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4479057490825653},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.407576322555542},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3355643153190613},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.3276914358139038},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1986253559589386},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12628135085105896},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11152568459510803},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07157924771308899}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147606611251831},{"id":"https://openalex.org/C105303287","wikidata":"https://www.wikidata.org/wiki/Q936692","display_name":"Comb filter","level":3,"score":0.5913867950439453},{"id":"https://openalex.org/C104247578","wikidata":"https://www.wikidata.org/wiki/Q4779368","display_name":"Aperiodic graph","level":2,"score":0.5797963738441467},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.5572651624679565},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5357306003570557},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5245176553726196},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4529593586921692},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4479057490825653},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.407576322555542},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3355643153190613},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3276914358139038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1986253559589386},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12628135085105896},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11152568459510803},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07157924771308899},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11130","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11130","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2037661079","https://openalex.org/W2036697162","https://openalex.org/W2140812588","https://openalex.org/W2411113819","https://openalex.org/W2072887367","https://openalex.org/W2339191433","https://openalex.org/W2332386680","https://openalex.org/W2561315646","https://openalex.org/W2248621902","https://openalex.org/W2368649523"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,8,26,35,59,80],"unified":[4,20,36],"source-filter":[5,37],"network":[6,39,85],"with":[7,30],"harmonic-plus-noise":[9],"source":[10,50,73,82],"excitation":[11,51,74,83],"generation":[12,84],"mechanism.":[13],"In":[14],"our":[15],"previous":[16],"work,":[17],"we":[18],"proposed":[19],"Source-Filter":[21],"GAN":[22],"(uSFGAN)":[23],"for":[24],"developing":[25],"high-fidelity":[27],"neural":[28,38],"vocoder":[29],"flexible":[31],"voice":[32,138],"controllability":[33],"using":[34],"architecture.":[40],"However,":[41],"the":[42,48,65,72,112,123,128,132,137],"capability":[43],"of":[44,99,107,131],"uSFGAN":[45,125,134],"to":[46,104],"model":[47],"aperiodic":[49,90],"signal":[52],"is":[53,57,92,101],"insufficient,":[54],"and":[55,67,76,89,117],"there":[56],"still":[58],"gap":[60],"in":[61,111],"sound":[62,78,129],"quality":[63,130],"between":[64],"natural":[66],"generated":[68,77],"speech.":[69],"To":[70],"improve":[71],"modeling":[75],"quality,":[79],"new":[81],"separately":[86],"generating":[87],"periodic":[88],"components":[91],"proposed.":[93],"The":[94],"advanced":[95],"adversarial":[96],"training":[97],"procedure":[98],"HiFiGAN":[100],"also":[102],"adopted":[103],"replace":[105],"that":[106,122],"Parallel":[108],"WaveGAN":[109],"used":[110],"original":[113],"uSFGAN.":[114],"Both":[115],"objective":[116],"subjective":[118],"evaluation":[119],"results":[120],"show":[121],"modified":[124],"significantly":[126],"improves":[127],"basic":[133],"while":[135],"maintaining":[136],"controllability.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}