{"id":"https://openalex.org/W4372260218","doi":"https://doi.org/10.1109/icassp49357.2023.10096481","title":"Analysis Of Noisy-Target Training For Dnn-Based Speech Enhancement","display_name":"Analysis Of Noisy-Target Training For Dnn-Based Speech Enhancement","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260218","doi":"https://doi.org/10.1109/icassp49357.2023.10096481"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5005224645","display_name":"Takuya Fujimura","orcid":null},"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":"Takuya Fujimura","raw_affiliation_strings":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006808971","display_name":"Tomoki Toda","orcid":null},"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":["Nagoya University,Japan","Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9945999979972839,"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":0.8203492164611816},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7229353785514832},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7134142518043518},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5845407843589783},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5660227537155151},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5242403149604797},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5234824419021606},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5142247676849365},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4301583468914032},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42236387729644775},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4180881977081299},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41766831278800964},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1608532965183258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8203492164611816},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7229353785514832},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7134142518043518},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5845407843589783},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5660227537155151},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5242403149604797},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5234824419021606},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5142247676849365},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4301583468914032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42236387729644775},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4180881977081299},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41766831278800964},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1608532965183258},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2141411743","https://openalex.org/W2288645994","https://openalex.org/W2289394825","https://openalex.org/W2291877678","https://openalex.org/W2603567530","https://openalex.org/W2793146153","https://openalex.org/W2933708090","https://openalex.org/W2952218014","https://openalex.org/W3015312544","https://openalex.org/W3016050488","https://openalex.org/W3035160371","https://openalex.org/W3093839391","https://openalex.org/W3094502228","https://openalex.org/W3099330747","https://openalex.org/W3122264812","https://openalex.org/W3161950572","https://openalex.org/W3166396011","https://openalex.org/W3177067699","https://openalex.org/W3207551191","https://openalex.org/W4292779060","https://openalex.org/W4292969786","https://openalex.org/W6631190155","https://openalex.org/W6778883912","https://openalex.org/W6784499681","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2294333436","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W4252682934","https://openalex.org/W2089240210","https://openalex.org/W642007152"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"(DNN)-based":[3],"speech":[4,10,25,39,60,149],"enhancement":[5,40],"usually":[6],"uses":[7],"a":[8,12,62,78,83,121,144],"clean":[9,24,81,131,151],"as":[11,61],"training":[13,48,63],"target.":[14],"However,":[15],"it":[16,69],"is":[17,29,125],"hard":[18],"to":[19,105,127],"collect":[20],"large":[21],"amounts":[22],"of":[23,37,47,109,117,147],"because":[26],"the":[27,35,45,115,128,140],"recording":[28],"very":[30],"costly.":[31],"In":[32,98,111],"other":[33],"words,":[34],"performance":[36,141],"current":[38],"has":[41,65,70,86,93],"been":[42,66,71,88,95],"limited":[43],"by":[44,142],"amount":[46,146],"data.":[49],"To":[50],"relax":[51],"this":[52,99],"limitation,":[53],"Noisy-target":[54],"Training":[55],"(NyTT)":[56],"that":[57,74,124,136],"utilizes":[58],"noisy":[59,148],"target":[64],"proposed.":[67],"Although":[68],"experimentally":[72],"shown":[73],"NyTT":[75],"can":[76,138],"train":[77],"DNN":[79],"without":[80],"speech,":[82],"detailed":[84],"analysis":[85],"not":[87,94],"conducted":[89],"and":[90],"its":[91],"behavior":[92],"understood":[96],"well.":[97],"paper,":[100],"we":[101,119,134,137],"conduct":[102],"various":[103],"analyses":[104],"deepen":[106],"our":[107],"understanding":[108],"NyTT.":[110],"addition,":[112],"based":[113],"on":[114],"property":[116],"NyTT,":[118],"propose":[120],"refined":[122],"method":[123,129],"comparable":[126],"using":[130,143],"speech.":[132,152],"Furthermore,":[133],"show":[135],"improve":[139],"huge":[145],"with":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}