{"id":"https://openalex.org/W2938983457","doi":"https://doi.org/10.1109/icassp.2019.8682320","title":"Investigations of Real-time Gaussian Fftnet and Parallel Wavenet Neural Vocoders with Simple Acoustic Features","display_name":"Investigations of Real-time Gaussian Fftnet and Parallel Wavenet Neural Vocoders with Simple Acoustic Features","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938983457","doi":"https://doi.org/10.1109/icassp.2019.8682320","mag":"2938983457"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/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"],"raw_orcid":null,"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/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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109350986","display_name":"Yoshinori Shiga","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":"Yoshinori Shiga","raw_affiliation_strings":["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"]}]},{"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"],"raw_orcid":null,"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7020","last_page":"7024"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9976000189781189,"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":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.7444568276405334},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6996597647666931},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6817799806594849},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5919361114501953},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5483761429786682},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4845272898674011},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4721163511276245},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.44337376952171326},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41898152232170105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3208119869232178},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1544371247291565},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12932679057121277},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12147551774978638},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.051570355892181396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444568276405334},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6996597647666931},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6817799806594849},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5919361114501953},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5483761429786682},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4845272898674011},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4721163511276245},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.44337376952171326},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41898152232170105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3208119869232178},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1544371247291565},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12932679057121277},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12147551774978638},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.051570355892181396},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W198589515","https://openalex.org/W1522301498","https://openalex.org/W2086161653","https://openalex.org/W2093450784","https://openalex.org/W2111284386","https://openalex.org/W2519091744","https://openalex.org/W2576309025","https://openalex.org/W2584032004","https://openalex.org/W2584393883","https://openalex.org/W2587284713","https://openalex.org/W2607821317","https://openalex.org/W2746474733","https://openalex.org/W2749651610","https://openalex.org/W2769810959","https://openalex.org/W2785516183","https://openalex.org/W2786868129","https://openalex.org/W2797310469","https://openalex.org/W2801291345","https://openalex.org/W2803595463","https://openalex.org/W2888932932","https://openalex.org/W2890983311","https://openalex.org/W2891813127","https://openalex.org/W2912237252","https://openalex.org/W2949382160","https://openalex.org/W2963175743","https://openalex.org/W2963300588","https://openalex.org/W2963522141","https://openalex.org/W2963589210","https://openalex.org/W2963782041","https://openalex.org/W2963975282","https://openalex.org/W2964115871","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W4294619240","https://openalex.org/W4298580827","https://openalex.org/W6631190155","https://openalex.org/W6732429163","https://openalex.org/W6733471323","https://openalex.org/W6736734616","https://openalex.org/W6743855016","https://openalex.org/W6748140763","https://openalex.org/W6748409065","https://openalex.org/W6753855596"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872"],"abstract_inverted_index":{"This":[0],"paper":[1],"examines":[2],"four":[3],"approaches":[4],"to":[5,75],"improving":[6],"real-time":[7,108,129],"neural":[8,66,89],"vocoders":[9,41,90,112],"with":[10,42,55,113,123],"simple":[11],"acoustic":[12],"features":[13],"(SAF)":[14],"constructed":[15],"from":[16,91],"fundamental":[17],"frequency":[18,82],"and":[19,39,53,68,107],"mel-cepstra":[20],"rather":[21],"than":[22],"mel-spectrograms.":[23],"The":[24,98],"investigations":[25],"are":[26],"as":[27],"follows:":[28],"1)":[29],"the":[30,45,58,70],"effectiveness":[31],"of":[32,47,60,72,83,95,100],"single":[33],"Gaussian":[34],"(SG)":[35],"autoregressive":[36],"(AR)":[37],"WaveNet":[38,50,106,132],"FFTNet":[40,111],"SAF,":[43,56],"2)":[44],"possibility":[46],"SG":[48,64,87,104,109,130],"parallel":[49,131],"vocoder":[51,133],"training":[52],"synthesis":[54,121],"3)":[57],"impact":[59],"noise":[61,114],"shaping":[62,115],"on":[63],"AR":[65,88,105,110],"vocoders,":[67],"4)":[69],"efficacy":[71],"bandwidth":[73,124],"extension":[74,125],"synthesize":[76],"speech":[77],"waveforms":[78],"at":[79],"a":[80,128],"sampling":[81],"24":[84],"kHz":[85],"by":[86],"SAF":[92,117],"for":[93],"that":[94,103],"16":[96],"kHz.":[97],"results":[99],"experiments":[101],"indicate":[102],"using":[116,138],"can":[118,134],"realize":[119],"sufficient":[120],"quality":[122],"effect.":[126],"Moreover,":[127],"also":[135],"be":[136],"trained":[137],"SAF.":[139]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
