{"id":"https://openalex.org/W4392904361","doi":"https://doi.org/10.1109/icassp48485.2024.10446960","title":"FIRNet: Fundamental Frequency Controllable Fast Neural Vocoder With Trainable Finite Impulse Response Filter","display_name":"FIRNet: Fundamental Frequency Controllable Fast Neural Vocoder With Trainable Finite Impulse Response Filter","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904361","doi":"https://doi.org/10.1109/icassp48485.2024.10446960"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/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":false,"raw_author_name":"Yamato Ohtani","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]},{"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/A5022943637","display_name":"Takuma Okamoto","orcid":"https://orcid.org/0000-0001-9913-4647"},"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","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]},{"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/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"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"]},{"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":"Tomoki Toda","raw_affiliation_strings":["National Institute of Information and Communications Technology,Japan","National Institute of Information and Communications Technology, Japan","Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114514387","display_name":"Hisashi Kawai","orcid":"https://orcid.org/0000-0002-0914-5092"},"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","National Institute of Information and Communications Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology,Japan","institution_ids":["https://openalex.org/I90023481"]},{"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10871","last_page":"10875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9991000294685364,"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":0.989300012588501,"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/finite-impulse-response","display_name":"Finite impulse response","score":0.7386033535003662},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.705746054649353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6387386322021484},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5703890323638916},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5669251680374146},{"id":"https://openalex.org/keywords/digital-filter","display_name":"Digital filter","score":0.5488685369491577},{"id":"https://openalex.org/keywords/impulse","display_name":"Impulse (physics)","score":0.5474477410316467},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5205667614936829},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.48577335476875305},{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.4485088288784027},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.44187384843826294},{"id":"https://openalex.org/keywords/infinite-impulse-response","display_name":"Infinite impulse response","score":0.4322056770324707},{"id":"https://openalex.org/keywords/filter-design","display_name":"Filter design","score":0.4222612679004669},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3549897074699402},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32296937704086304},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.21911123394966125},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1219489574432373},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11150774359703064},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0966484546661377},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.08059269189834595},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07993525266647339}],"concepts":[{"id":"https://openalex.org/C198386975","wikidata":"https://www.wikidata.org/wiki/Q117785","display_name":"Finite impulse response","level":2,"score":0.7386033535003662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.705746054649353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6387386322021484},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5703890323638916},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5669251680374146},{"id":"https://openalex.org/C36390408","wikidata":"https://www.wikidata.org/wiki/Q1163067","display_name":"Digital filter","level":3,"score":0.5488685369491577},{"id":"https://openalex.org/C70836080","wikidata":"https://www.wikidata.org/wiki/Q837940","display_name":"Impulse (physics)","level":2,"score":0.5474477410316467},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5205667614936829},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.48577335476875305},{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.4485088288784027},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.44187384843826294},{"id":"https://openalex.org/C183816354","wikidata":"https://www.wikidata.org/wiki/Q665617","display_name":"Infinite impulse response","level":4,"score":0.4322056770324707},{"id":"https://openalex.org/C22597639","wikidata":"https://www.wikidata.org/wiki/Q5449227","display_name":"Filter design","level":3,"score":0.4222612679004669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3549897074699402},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32296937704086304},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.21911123394966125},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1219489574432373},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11150774359703064},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0966484546661377},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.08059269189834595},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07993525266647339},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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:10.1109/icassp48485.2024.10446960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":31,"referenced_works":["https://openalex.org/W2012086895","https://openalex.org/W2395578248","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2519648275","https://openalex.org/W2593414223","https://openalex.org/W2747070883","https://openalex.org/W2749651610","https://openalex.org/W2899663614","https://openalex.org/W2963091184","https://openalex.org/W2990440871","https://openalex.org/W3041738652","https://openalex.org/W3045000780","https://openalex.org/W3130168980","https://openalex.org/W3160919572","https://openalex.org/W4280575909","https://openalex.org/W4297841815","https://openalex.org/W4372262501","https://openalex.org/W4375869034","https://openalex.org/W4382296240","https://openalex.org/W4385823165","https://openalex.org/W4385993913","https://openalex.org/W4386076493","https://openalex.org/W6631190155","https://openalex.org/W6711777497","https://openalex.org/W6748409065","https://openalex.org/W6755977528","https://openalex.org/W6767111847","https://openalex.org/W6780226713","https://openalex.org/W6782760101","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W4312785053","https://openalex.org/W2142009384","https://openalex.org/W3140661709","https://openalex.org/W2810377961","https://openalex.org/W2031892245","https://openalex.org/W3208746183","https://openalex.org/W2898725502","https://openalex.org/W2058863651","https://openalex.org/W2115724989","https://openalex.org/W4308935600"],"abstract_inverted_index":{"Some":[0],"neural":[1,49,85],"vocoders":[2,34,117],"with":[3,32,56,100],"fundamental":[4],"frequency":[5],"(f":[6],"<inf":[7,121],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[8,122],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</inf>":[9,123],")":[10],"control":[11],"have":[12],"succeeded":[13],"in":[14],"performing":[15],"real-time":[16],"inference":[17,40,68,112],"on":[18,36,52],"a":[19,48,66,96],"single":[20],"CPU":[21],"while":[22,118],"preserving":[23],"the":[24,27,53,74,84,88],"quality":[25],"of":[26],"synthetic":[28],"speech.":[29],"However,":[30],"compared":[31],"legacy":[33,71,116],"based":[35,51],"signal":[37,99],"processing,":[38],"their":[39],"speeds":[41],"are":[42,81],"still":[43],"low.":[44],"This":[45],"paper":[46],"proposes":[47],"vocoder":[50],"source-filter":[54],"model":[55],"trainable":[57],"time-variant":[58],"finite":[59],"impulse":[60],"response":[61],"(FIR)":[62],"filters,":[63],"to":[64,70,115],"achieve":[65,110],"similar":[67,114],"speed":[69,113],"vocoders.":[72],"In":[73],"proposed":[75],"model,":[76],"FIRNet,":[77],"multiple":[78],"FIR":[79,102],"coefficients":[80],"predicted":[82],"using":[83],"networks,":[86],"and":[87,125],"speech":[89,127],"waveform":[90],"is":[91],"then":[92],"generated":[93],"by":[94],"convolving":[95],"mixed":[97],"excitation":[98],"these":[101],"coefficients.":[103],"Experimental":[104],"results":[105],"show":[106],"that":[107],"FIRNet":[108],"can":[109],"an":[111],"maintaining":[119],"f":[120],"controllability":[124],"natural":[126],"quality.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
