{"id":"https://openalex.org/W2790645443","doi":"https://doi.org/10.1109/taslp.2018.2818408","title":"Mel-Cepstrum-Based Quantization Noise Shaping Applied to Neural-Network-Based Speech Waveform Synthesis","display_name":"Mel-Cepstrum-Based Quantization Noise Shaping Applied to Neural-Network-Based Speech Waveform Synthesis","publication_year":2018,"publication_date":"2018-03-22","ids":{"openalex":"https://openalex.org/W2790645443","doi":"https://doi.org/10.1109/taslp.2018.2818408","mag":"2790645443"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2818408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2818408","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5101948311","display_name":"Takenori Yoshimura","orcid":"https://orcid.org/0000-0003-3964-5677"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takenori Yoshimura","raw_affiliation_strings":["Nagoya Kogyo Daigaku, Nagoya, Aichi, JP"],"raw_orcid":"https://orcid.org/0000-0003-3964-5677","affiliations":[{"raw_affiliation_string":"Nagoya Kogyo Daigaku, Nagoya, Aichi, JP","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067594810","display_name":"Kei Hashimoto","orcid":"https://orcid.org/0000-0003-2081-0396"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Hashimoto","raw_affiliation_strings":["Nagoya Kogyo Daigaku, Nagoya, Aichi, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Kogyo Daigaku, Nagoya, Aichi, JP","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049909008","display_name":"Keiichiro Oura","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichiro Oura","raw_affiliation_strings":["Nagoya Kogyo Daigaku, Nagoya, Aichi, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Kogyo Daigaku, Nagoya, Aichi, JP","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":["Nagoya Kogyo Daigaku, Nagoya, Aichi, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Kogyo Daigaku, Nagoya, Aichi, JP","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Nagoya Kogyo Daigaku, Nagoya, Aichi, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Kogyo Daigaku, Nagoya, Aichi, JP","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":2.9648,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92594055,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"26","issue":"7","first_page":"1177","last_page":"1184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9927999973297119,"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/cepstrum","display_name":"Cepstrum","score":0.7517391443252563},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7288709878921509},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7255635261535645},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6232442855834961},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.594274640083313},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5374544262886047},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4970746338367462},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.4940965473651886},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48714014887809753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3576238453388214},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.12626439332962036},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12196603417396545},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11421936750411987}],"concepts":[{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.7517391443252563},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7288709878921509},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7255635261535645},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6232442855834961},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.594274640083313},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5374544262886047},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4970746338367462},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.4940965473651886},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48714014887809753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3576238453388214},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.12626439332962036},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12196603417396545},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11421936750411987},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2018.2818408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2818408","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3680276803","display_name":"Articulatory text-to-speech synthesis based on digital waveguide mesh driven by deep neural network","funder_award_id":"17K20004","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1505035441","https://openalex.org/W1522301498","https://openalex.org/W1527535554","https://openalex.org/W1719896327","https://openalex.org/W1766888123","https://openalex.org/W2040837017","https://openalex.org/W2049686551","https://openalex.org/W2064354100","https://openalex.org/W2079032518","https://openalex.org/W2093450784","https://openalex.org/W2096980176","https://openalex.org/W2102003408","https://openalex.org/W2105961477","https://openalex.org/W2106792148","https://openalex.org/W2111284386","https://openalex.org/W2145892079","https://openalex.org/W2267126114","https://openalex.org/W2338186431","https://openalex.org/W2360103489","https://openalex.org/W2471520273","https://openalex.org/W2478884216","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2749651610","https://openalex.org/W2949382160","https://openalex.org/W2953318193","https://openalex.org/W2964121744","https://openalex.org/W3177989406","https://openalex.org/W6631190155","https://openalex.org/W6675380101","https://openalex.org/W6732429163","https://openalex.org/W6743855016","https://openalex.org/W6798679566"],"related_works":["https://openalex.org/W4246349004","https://openalex.org/W2181871477","https://openalex.org/W2061163896","https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2432604435","https://openalex.org/W2373675101","https://openalex.org/W4385672897","https://openalex.org/W2089229568"],"abstract_inverted_index":{"This":[0],"paper":[1,55],"presents":[2],"a":[3,58,83],"mel-cepstrum-based":[4],"quantization":[5,45],"noise":[6,41],"shaping":[7],"method":[8,36,65],"for":[9,86],"improving":[10],"the":[11,28,34,39,44,63,67,70,77,99],"quality":[12,94],"of":[13,30,62,69],"synthetic":[14],"speech":[15,19,50,88,93],"generated":[16],"by":[17,43,98],"neural-network-based":[18,49,87],"waveform":[20,51,89],"synthesis":[21,52],"systems.":[22,53],"Since":[23],"mel-cepstral":[24],"coefficients":[25],"closely":[26],"match":[27],"characteristics":[29],"human":[31],"auditory":[32],"perception,":[33],"proposed":[35,64,100],"effectively":[37],"masks":[38],"white":[40],"introduced":[42],"typically":[46],"used":[47],"in":[48],"The":[54],"also":[56],"describes":[57],"computationally":[59],"efficient":[60],"implementation":[61],"using":[66,76],"structure":[68],"mel-log":[71],"spectrum":[72],"approximation":[73],"filter.":[74],"Experiments":[75],"WaveNet":[78],"generative":[79],"model,":[80],"which":[81],"is":[82,95],"state-of-the-art":[84],"model":[85],"synthesis,":[90],"showed":[91],"that":[92],"significantly":[96],"improved":[97],"method.":[101]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":6}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}