{"id":"https://openalex.org/W2797310469","doi":"https://doi.org/10.1109/icassp.2018.8461332","title":"An Investigation of Noise Shaping with Perceptual Weighting for Wavenet-Based Speech Generation","display_name":"An Investigation of Noise Shaping with Perceptual Weighting for Wavenet-Based Speech Generation","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2797310469","doi":"https://doi.org/10.1109/icassp.2018.8461332","mag":"2797310469"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5100925892","display_name":"Kentaro Tachibana","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":"Kentaro Tachibana","raw_affiliation_strings":["National Institute of Information and Communications Technology, DeNA Co. Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, DeNA Co. Ltd., 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, DeNA Co. Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, DeNA Co. Ltd., 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, DeNA Co. Ltd., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, DeNA Co. Ltd., 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":49,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5664","last_page":"5668"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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/speech-recognition","display_name":"Speech recognition","score":0.7286472320556641},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6997590065002441},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5536261796951294},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49326127767562866},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.46121537685394287},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.44609689712524414},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4422869086265564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41067802906036377},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.377002477645874},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24898740649223328},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24051198363304138},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17181316018104553},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12504708766937256},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08656930923461914}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7286472320556641},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6997590065002441},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5536261796951294},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49326127767562866},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.46121537685394287},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.44609689712524414},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4422869086265564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41067802906036377},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.377002477645874},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24898740649223328},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24051198363304138},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17181316018104553},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12504708766937256},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08656930923461914},{"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/icassp.2018.8461332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1658344067","https://openalex.org/W1965255698","https://openalex.org/W2049686551","https://openalex.org/W2093450784","https://openalex.org/W2102003408","https://openalex.org/W2103791750","https://openalex.org/W2111284386","https://openalex.org/W2129142580","https://openalex.org/W2194775991","https://openalex.org/W2296704011","https://openalex.org/W2423557781","https://openalex.org/W2471520273","https://openalex.org/W2507771204","https://openalex.org/W2519091744","https://openalex.org/W2519648275","https://openalex.org/W2584032004","https://openalex.org/W2584393883","https://openalex.org/W2591927543","https://openalex.org/W2619368999","https://openalex.org/W2674088828","https://openalex.org/W2746474733","https://openalex.org/W2747161606","https://openalex.org/W2748163399","https://openalex.org/W2749651610","https://openalex.org/W2785516183","https://openalex.org/W2786868129","https://openalex.org/W2901997113","https://openalex.org/W2964301388","https://openalex.org/W4298642009","https://openalex.org/W6675380101","https://openalex.org/W6675672303","https://openalex.org/W6682407441","https://openalex.org/W6743855016","https://openalex.org/W6756197946"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W164103134","https://openalex.org/W2040545019","https://openalex.org/W2787352659","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"We":[0,65,152],"propose":[1],"a":[2,19,26,31,109,132],"noise":[3,43,68,93,100,119,128],"shaping":[4,129],"method":[5,130,165],"to":[6,103,136,141,158],"improve":[7],"the":[8,47,59,63,75,82,85,88,92,114,122,126,143,148,160,163,172,176],"sound":[9,173],"quality":[10,174],"of":[11,62,87,117,147,162,175],"speech":[12,124,178],"signals":[13,36,44,69,94,101,120],"generated":[14,37,50,123,177],"by":[15,38,46,51],"WaveNet,":[16,137],"which":[17],"is":[18,78,95],"convolutional":[20],"neural":[21],"network":[22],"(CNN)":[23],"that":[24,72,168],"predicts":[25],"waveform":[27,53],"sample":[28],"sequence":[29],"as":[30,55],"discrete":[32,56],"symbol":[33],"sequence.":[34],"Speech":[35],"WaveNet":[39],"often":[40],"suffer":[41],"from":[42],"caused":[45],"quantization":[48,83,89],"error":[49,61,77,90],"representing":[52],"samples":[54],"symbols":[57],"and":[58,70,98,155,166],"prediction":[60,76],"CNN.":[64],"analyze":[66],"these":[67,118],"show":[71],"1)":[73],"since":[74],"much":[79],"larger":[80],"than":[81],"error,":[84],"effect":[86,116],"on":[91,121],"practically":[96],"negligible,":[97],"2)":[99],"tend":[102],"cause":[104],"large":[105],"spectral":[106],"distortion":[107],"in":[108],"high-frequency":[110],"band.":[111],"To":[112],"alleviate":[113],"adverse":[115],"signals,":[125],"proposed":[127,164],"applies":[131],"perceptual":[133],"weighting":[134],"filter":[135],"making":[138],"it":[139,169],"possible":[140],"use":[142],"frequency":[144],"masking":[145],"properties":[146],"human":[149],"auditory":[150],"system.":[151],"conducted":[153],"objective":[154],"subjective":[156],"evaluations":[157],"investigate":[159],"effectiveness":[161],"demonstrated":[167],"significantly":[170],"improved":[171],"signals.":[179]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}