{"id":"https://openalex.org/W3145039504","doi":"https://doi.org/10.1109/slt48900.2021.9383611","title":"Denoising-and-Dereverberation Hierarchical Neural Vocoder for Robust Waveform Generation","display_name":"Denoising-and-Dereverberation Hierarchical Neural Vocoder for Robust Waveform Generation","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3145039504","doi":"https://doi.org/10.1109/slt48900.2021.9383611","mag":"3145039504"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["University of Science and Technology of China, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358569","display_name":"Haoyu Li","orcid":"https://orcid.org/0000-0002-7102-8348"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haoyu Li","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Ling","raw_affiliation_strings":["University of Science and Technology of China, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"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":"1","issue":null,"first_page":"477","last_page":"484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.998199999332428,"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":0.7788624167442322},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7132079005241394},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7086770534515381},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.614318311214447},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.6053118109703064},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5130995512008667},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4633283019065857},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.43855273723602295},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.4373569190502167},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.41024279594421387},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.32486680150032043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2935243248939514},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.18882200121879578},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.11162355542182922},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09872335195541382},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08768293261528015},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06659671664237976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788624167442322},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7132079005241394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7086770534515381},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.614318311214447},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.6053118109703064},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5130995512008667},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4633283019065857},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.43855273723602295},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.4373569190502167},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.41024279594421387},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.32486680150032043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2935243248939514},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.18882200121879578},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.11162355542182922},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09872335195541382},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08768293261528015},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06659671664237976},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383611","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383611","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W190060899","https://openalex.org/W1952824372","https://openalex.org/W1996304098","https://openalex.org/W2044893557","https://openalex.org/W2067295501","https://openalex.org/W2115098197","https://openalex.org/W2136682440","https://openalex.org/W2144404214","https://openalex.org/W2291877678","https://openalex.org/W2292984643","https://openalex.org/W2519091744","https://openalex.org/W2749651610","https://openalex.org/W2769810959","https://openalex.org/W2792263949","https://openalex.org/W2801554275","https://openalex.org/W2803595463","https://openalex.org/W2889329491","https://openalex.org/W2902132730","https://openalex.org/W2935693977","https://openalex.org/W2940385941","https://openalex.org/W2940417587","https://openalex.org/W2951310434","https://openalex.org/W2953030256","https://openalex.org/W2954386831","https://openalex.org/W2962879692","https://openalex.org/W2963103134","https://openalex.org/W2963300588","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2963782041","https://openalex.org/W2963975282","https://openalex.org/W2964243274","https://openalex.org/W2972309641","https://openalex.org/W2990440871","https://openalex.org/W3016129867","https://openalex.org/W3095749709","https://openalex.org/W3096080837","https://openalex.org/W3096643087","https://openalex.org/W3104557543","https://openalex.org/W3141523618","https://openalex.org/W4289242435","https://openalex.org/W4294619240","https://openalex.org/W4295521014","https://openalex.org/W4385245566","https://openalex.org/W6677210350","https://openalex.org/W6735913928","https://openalex.org/W6739901393","https://openalex.org/W6749927861","https://openalex.org/W6753855596","https://openalex.org/W6755592152","https://openalex.org/W6756251360"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2022849831","https://openalex.org/W2037265366","https://openalex.org/W2026603686","https://openalex.org/W2987432963","https://openalex.org/W2053167664","https://openalex.org/W2780118011","https://openalex.org/W2079152323","https://openalex.org/W2128388559"],"abstract_inverted_index":{"This":[0,39],"paper":[1],"presents":[2],"a":[3,19,121,145,163],"denoising":[4,41,89],"and":[5,14,42,67,77,90,125,147,152,156,162,178],"dereverberation":[6,43],"hierarchical":[7],"neural":[8,101,166],"vocoder":[9,140,161,173],"(DNR-HiNet)":[10],"to":[11,73,82,143,174],"convert":[12],"noisy":[13,66,151],"reverberant":[15,68,153],"acoustic":[16,56,154],"features":[17,155],"into":[18],"clean":[20,48,106,116],"speech":[21,175,186],"waveform.":[22],"We":[23,168],"implement":[24],"it":[25],"mainly":[26],"by":[27,99],"modifying":[28],"the":[29,35,61,65,74,83,104,111,114,131,138,158,171],"amplitude":[30,50],"spectrum":[31],"predictor":[32],"(ASP)":[33],"in":[34,130],"original":[36,159],"HiNet":[37,160],"vocoder.":[38],"modified":[40],"ASP":[44],"(DNR-ASP)":[45],"can":[46],"predict":[47],"log":[49],"spectra":[51],"(LAS)":[52],"from":[53],"input":[54],"degraded":[55],"features.":[57],"To":[58,108],"achieve":[59],"this,":[60],"DNR-ASP":[62],"first":[63],"predicts":[64],"LAS,":[69,117],"noise":[70,75],"LAS":[71,95],"related":[72,81],"information,":[76],"room":[78],"impulse":[79],"response":[80],"reverberation":[84],"information":[85],"then":[86,97],"performs":[87],"initial":[88,93],"dereverberation.":[91],"The":[92,133],"processed":[94],"are":[96],"enhanced":[98],"another":[100],"network":[102],"as":[103],"final":[105],"LAS.":[107],"further":[109],"improve":[110],"quality":[112],"of":[113],"generated":[115],"we":[118],"also":[119,169],"introduce":[120],"bandwidth":[122],"extension":[123,128],"model":[124,129],"frequency":[126],"resolution":[127],"DNR-ASP.":[132],"experimental":[134],"results":[135],"indicate":[136],"that":[137],"DNR-HiNet":[139,172],"was":[141,181],"able":[142],"generate":[144],"denoised":[146],"dereverberated":[148],"waveform":[149],"given":[150],"outperformed":[157],"few":[164],"other":[165],"vocoders.":[167],"applied":[170],"enhancement":[176,187],"tasks,":[177],"its":[179],"performance":[180],"competitive":[182],"with":[183],"several":[184],"advanced":[185],"methods.":[188]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}