{"id":"https://openalex.org/W7140302106","doi":"https://doi.org/10.1109/access.2026.3677555","title":"Controllable End-to-End Neural Source\u2013Filter Vocoder With Low-Dimensional Speech Parameters and Data Augmentation","display_name":"Controllable End-to-End Neural Source\u2013Filter Vocoder With Low-Dimensional Speech Parameters and Data Augmentation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140302106","doi":"https://doi.org/10.1109/access.2026.3677555"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3677555","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3677555","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3677555","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sumiharu Kobayashi","orcid":"https://orcid.org/0009-0008-4860-5400"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sumiharu Kobayashi","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Sendai, Japan"],"raw_orcid":"https://orcid.org/0009-0008-4860-5400","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Sendai, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112342909","display_name":"Tetsuo Kosaka","orcid":null},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuo Kosaka","raw_affiliation_strings":["Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1321-641X","affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Yamagata University, Yonezawa, Japan","institution_ids":["https://openalex.org/I112524849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130560989","display_name":"Takashi Nose","orcid":null},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Sendai, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2278-0429","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Sendai, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33277971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"50191","last_page":"50203"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.19550000131130219,"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":0.19550000131130219,"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":0.1720999926328659,"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":0.07050000131130219,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.448199987411499},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3865000009536743},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.322299987077713},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.29010000824928284},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.27790001034736633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731999754905701},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6266000270843506},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38119998574256897},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.322299987077713},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25290000438690186},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2395000010728836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3677555","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3677555","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d4e29cf7cf0e40f0be54e02b31d4cb59","is_oa":true,"landing_page_url":"https://doaj.org/article/d4e29cf7cf0e40f0be54e02b31d4cb59","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 50191-50203 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3677555","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3677555","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"neural":[1,44,69,79],"vocoders":[2],"synthesize":[3],"speech":[4,15,25,30,52,64,84,88,118,132],"waveforms":[5,85],"from":[6,61,86],"high-dimensional":[7],"spectrograms,":[8],"making":[9],"it":[10],"difficult":[11],"to":[12,42,66,93,122],"control":[13,100],"individual":[14],"parameters":[16,31,35],"such":[17],"asF0and":[18],"formants.":[19],"Previous":[20],"research":[21],"has":[22],"proposed":[23,147],"a":[24,43,76,103],"synthesis":[26,96],"system":[27],"that":[28,38,81,113,126],"controls":[29],"by":[32,101],"converting":[33],"low-dimensional":[34,87],"into":[36],"spectrograms":[37],"serve":[39],"as":[40],"input":[41],"vocoder.":[45,70],"However,":[46],"the":[47,50,55,62,68,95,114,138,146],"quality":[48,97,120],"of":[49,127,145],"synthesized":[51],"degrades":[53],"because":[54],"generated":[56],"spectral":[57],"time":[58],"series":[59],"differs":[60],"natural":[63],"used":[65],"train":[67],"In":[71],"this":[72],"study,":[73],"we":[74,91],"propose":[75],"controllable":[77],"end-to-end":[78],"vocoder":[80],"directly":[82],"synthesizes":[83,117],"parameters.":[89,133],"Furthermore,":[90],"aim":[92],"improve":[94],"during":[98],"speech-parameter":[99],"introducing":[102],"source\u2013filter":[104],"model":[105],"and":[106],"employing":[107],"data":[108,135],"augmentation.":[109],"Experimental":[110],"evaluations":[111],"show":[112],"source-filter-based":[115],"method":[116],"with":[119],"equal":[121],"or":[123],"better":[124],"than":[125],"conventional":[128],"approaches":[129],"when":[130],"controlling":[131],"Additionally,":[134],"augmentation":[136],"improved":[137],"robustness":[139],"ofF0and":[140],"formant":[141],"controls.":[142],"A":[143],"demonstration":[144],"methods":[148],"is":[149],"available":[150],"online":[151],"(https://misumisumi.github.io/myprojects/end-to-end-neural-formant-synthesis).":[152]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-03-26T00:00:00"}