{"id":"https://openalex.org/W7148309886","doi":"https://doi.org/10.1109/asru65441.2025.11434739","title":"Voice Factor Control Using FIR-Based Fast Neural Vocoder for Speech Generation Applications","display_name":"Voice Factor Control Using FIR-Based Fast Neural Vocoder for Speech Generation Applications","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148309886","doi":"https://doi.org/10.1109/asru65441.2025.11434739"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5018533235","display_name":"Yamato Ohtani","orcid":"https://orcid.org/0009-0009-2961-2821"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yamato Ohtani","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132826953","display_name":"Takuma Okamoto","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Okamoto","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132801075","display_name":"Tomoki Toda","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132811394","display_name":"Hisashi Kawai","orcid":null},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hisashi Kawai","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018533235"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87551762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7620999813079834,"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":0.7620999813079834,"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":0.0754999965429306,"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/T10863","display_name":"Voice and Speech Disorders","score":0.02669999934732914,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4535999894142151},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41029998660087585},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.388700008392334},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3684999942779541},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.34150001406669617},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3377000093460083}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.678600013256073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658999919891357},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41029998660087585},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.34150001406669617},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":18,"referenced_works":["https://openalex.org/W2012086895","https://openalex.org/W2102003408","https://openalex.org/W2106792148","https://openalex.org/W2128413412","https://openalex.org/W2471520273","https://openalex.org/W2519648275","https://openalex.org/W3150572638","https://openalex.org/W4224612669","https://openalex.org/W4372266915","https://openalex.org/W4385822605","https://openalex.org/W4385993913","https://openalex.org/W4385993916","https://openalex.org/W4386076493","https://openalex.org/W4392903256","https://openalex.org/W4392908903","https://openalex.org/W4402112060","https://openalex.org/W4402112249","https://openalex.org/W4409761419"],"related_works":[],"abstract_inverted_index":{"We":[0,108],"have":[1,62],"proposed":[2],"a":[3],"fast":[4],"neural":[5,51,97],"vocoder":[6,35],"based":[7],"on":[8],"the":[9,72,124],"source-filter":[10],"model":[11],"introducing":[12],"finite":[13],"impulse":[14],"response":[15],"(FIR)":[16],"filters":[17],"called":[18],"FIRNet.":[19],"FIRNet":[20,94,114],"is":[21,77,121,126],"highly":[22],"compatible":[23],"with":[24,115],"digital":[25],"signal":[26],"processing":[27],"(DSP)":[28],"and":[29,37,45,59,70,123],"can,":[30],"therefore,":[31],"generate":[32,66],"waveforms":[33],"from":[34],"parameters":[36],"modified":[38],"voice":[39,57,86,105,117],"factors,":[40,87],"such":[41,55],"as":[42,56],"tone,":[43],"intonation,":[44],"timbre,":[46,75],"using":[47,113],"DSP.":[48],"Although":[49],"modern":[50,96],"waveform":[52,98],"generation":[53,99],"systems,":[54,100],"conversion":[58],"text-to-speech":[60],"(TTS),":[61],"been":[63],"able":[64],"to":[65,82,95],"human-like":[67],"synthetic":[68],"speech":[69],"imitate":[71],"reference":[73],"speaker\u2019s":[74],"it":[76],"challenging":[78],"for":[79],"these":[80],"systems":[81],"manually":[83],"control":[84],"arbitrary":[85,104],"unlike":[88],"traditional":[89],"TTS":[90],"systems.":[91],"By":[92],"applying":[93],"they":[101],"can":[102],"achieve":[103],"factor":[106,118],"controllability.":[107],"will":[109],"demonstrate":[110],"two":[111],"applications":[112],"DSP-based":[116],"controls:":[119],"one":[120],"analysis-synthesis,":[122],"other":[125],"text-to-speech.":[127]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}