{"id":"https://openalex.org/W2920974976","doi":"https://doi.org/10.23919/apsipa.2018.8659691","title":"Generative approach using the noise generation models for DNN-based speech synthesis trained from noisy speech","display_name":"Generative approach using the noise generation models for DNN-based speech synthesis trained from noisy speech","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2920974976","doi":"https://doi.org/10.23919/apsipa.2018.8659691","mag":"2920974976"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659691","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5023936972","display_name":"Masakazu Une","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masakazu Une","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083394213","display_name":"Yuki Saito","orcid":"https://orcid.org/0000-0002-7967-2613"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Saito","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071479017","display_name":"Daichi Kitamura","orcid":"https://orcid.org/0000-0003-1117-7939"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daichi Kitamura","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075732053","display_name":"Ryoichi Miyazaki","orcid":"https://orcid.org/0000-0002-5023-5380"},"institutions":[{"id":"https://openalex.org/I4210142609","display_name":"National Institute of Technology, Tokuyama College","ror":"https://ror.org/046jx2h22","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120810","https://openalex.org/I4210142609"]},{"id":"https://openalex.org/I1315201533","display_name":"Tokuyama (Japan)","ror":"https://ror.org/04zj4k586","country_code":"JP","type":"company","lineage":["https://openalex.org/I1315201533"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoichi Miyazaki","raw_affiliation_strings":["National Institute of Technology, Tokuyama College, Gakuendai Shunan, Yamaguchi, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Technology, Tokuyama College, Gakuendai Shunan, Yamaguchi, Japan","institution_ids":["https://openalex.org/I1315201533","https://openalex.org/I4210142609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023936972"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18941736,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"340","last_page":"344"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.794310450553894},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7072242498397827},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6241727471351624},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6235044598579407},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5160212516784668},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5142588019371033},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.5063282251358032},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4670051336288452},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4176861643791199},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4148722290992737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.363574743270874},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.21157696843147278},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11320069432258606},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06679880619049072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794310450553894},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7072242498397827},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6241727471351624},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6235044598579407},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5160212516784668},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5142588019371033},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.5063282251358032},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4670051336288452},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4176861643791199},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4148722290992737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.363574743270874},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.21157696843147278},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11320069432258606},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06679880619049072},{"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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659691","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W187033940","https://openalex.org/W1600722501","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2061678360","https://openalex.org/W2099471712","https://openalex.org/W2102003408","https://openalex.org/W2114508388","https://openalex.org/W2120847449","https://openalex.org/W2125389028","https://openalex.org/W2128653836","https://openalex.org/W2129142580","https://openalex.org/W2146502635","https://openalex.org/W2293049663","https://openalex.org/W2471520273","https://openalex.org/W2514828952","https://openalex.org/W2519091744","https://openalex.org/W2523904137","https://openalex.org/W2524365899","https://openalex.org/W2527515520","https://openalex.org/W2607404225","https://openalex.org/W2740345664","https://openalex.org/W2747161606","https://openalex.org/W2749881488","https://openalex.org/W2750393323","https://openalex.org/W2765486990","https://openalex.org/W2806666542","https://openalex.org/W2962916039","https://openalex.org/W2963971656","https://openalex.org/W4320013936","https://openalex.org/W6607663849","https://openalex.org/W6675380101","https://openalex.org/W6681435938","https://openalex.org/W6752467913","https://openalex.org/W7075637324"],"related_works":["https://openalex.org/W3211091508","https://openalex.org/W193702574","https://openalex.org/W1842536210","https://openalex.org/W1967664370","https://openalex.org/W2155010696","https://openalex.org/W1979693044","https://openalex.org/W1999835922","https://openalex.org/W2063862874","https://openalex.org/W72660888","https://openalex.org/W2154415461"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,33,118],"generative":[4,119],"approach":[5],"to":[6,19,39,91,135,148],"construct":[7,20],"high-quality":[8,21],"speech":[9,16,22,28,42,45,69,93,130,194],"synthesis":[10,46,70,94,131],"from":[11],"noisy":[12,34,41,151],"speech.":[13,152],"Studio-quality":[14],"recorded":[15,31],"is":[17,48],"required":[18],"synthesis,":[23],"but":[24],"most":[25],"of":[26,63,126,139,150,162,192],"existing":[27],"has":[29,81],"been":[30,82],"in":[32,103,175,190],"environment.":[35],"A":[36],"common":[37],"method":[38,168,185,189],"use":[40],"for":[43],"training":[44,121],"models":[47,95,115,132],"reducing":[49],"the":[50,53,97,108,127,137,143,154,160,163,166,171,176,183,187],"noise":[51,98,113,146,155],"before":[52],"vocoder-based":[54],"parameterization.":[55],"However,":[56],"such":[57],"multi-step":[58],"processes":[59],"cause":[60],"an":[61],"accumulation":[62],"spectral":[64,77,172],"distortion.":[65],"Meanwhile,":[66],"statistical":[67],"parametric":[68],"(SPSS)":[71],"without":[72],"vocoders,":[73],"which":[74],"directly":[75],"generates":[76,124],"parameters":[78,158],"or":[79],"waveforms,":[80],"proposed":[83,109,167,184],"recently.":[84],"The":[85,129],"vocoder-free":[86],"SPSS":[87],"will":[88],"enable":[89],"us":[90],"train":[92],"considering":[96],"addition":[99],"process":[100],"generally":[101],"used":[102],"signal":[104],"processing":[105],"research.":[106],"In":[107],"approach,":[110],"newly":[111],"introduced":[112],"generation":[114,156],"trained":[116,134],"by":[117],"adversarial":[120],"algorithm":[122],"randomly":[123,144],"spectra":[125,149],"noise.":[128],"are":[133],"make":[136],"sum":[138],"their":[140],"output":[141],"and":[142],"generated":[145],"close":[147],"Because":[153],"model":[157],"fit":[159],"spectrum":[161],"observed":[164],"noise,":[165],"can":[169],"alleviate":[170],"distortion":[173],"found":[174],"conventional":[177,188],"method.":[178],"Experimental":[179],"results":[180],"demonstrate":[181],"that":[182],"outperforms":[186],"terms":[191],"synthetic":[193],"quality.":[195]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}