{"id":"https://openalex.org/W4388821018","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317412","title":"NADiffuSE: Noise-aware Diffusion-based Model for Speech Enhancement","display_name":"NADiffuSE: Noise-aware Diffusion-based Model for Speech Enhancement","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821018","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317412"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5068985400","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0001-7724-1011"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Peking University,the School of Electronic and Computer Engineering,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,the School of Electronic and Computer Engineering,Shenzhen,China,518055","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043555011","display_name":"Dongchao Yang","orcid":"https://orcid.org/0000-0002-8905-224X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongchao Yang","raw_affiliation_strings":["Peking University,the School of Electronic and Computer Engineering,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,the School of Electronic and Computer Engineering,Shenzhen,China,518055","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034100208","display_name":"Qichen Ye","orcid":"https://orcid.org/0009-0005-7151-4257"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qichen Ye","raw_affiliation_strings":["Peking University,the School of Electronic and Computer Engineering,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,the School of Electronic and Computer Engineering,Shenzhen,China,518055","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078965698","display_name":"Bowen Cao","orcid":"https://orcid.org/0000-0002-4272-2381"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Cao","raw_affiliation_strings":["Peking University,the School of Electronic and Computer Engineering,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,the School of Electronic and Computer Engineering,Shenzhen,China,518055","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Peking University,the School of Electronic and Computer Engineering,Shenzhen,China,518055"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,the School of Electronic and Computer Engineering,Shenzhen,China,518055","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2416","last_page":"2423"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7192578911781311},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6713716983795166},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5528179407119751},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5100920796394348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4675919711589813},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.462749719619751},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.46244651079177856},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4178812503814697},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34117937088012695},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3238295316696167},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2292959988117218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7192578911781311},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6713716983795166},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5528179407119751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5100920796394348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4675919711589813},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.462749719619751},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.46244651079177856},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4178812503814697},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34117937088012695},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3238295316696167},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2292959988117218},{"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/apsipaasc58517.2023.10317412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc58517.2023.10317412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W160800111","https://openalex.org/W1959608418","https://openalex.org/W1989034586","https://openalex.org/W2044893557","https://openalex.org/W2078528584","https://openalex.org/W2094721231","https://openalex.org/W2129069237","https://openalex.org/W2141411743","https://openalex.org/W2291877678","https://openalex.org/W2403766732","https://openalex.org/W2519091744","https://openalex.org/W2603567530","https://openalex.org/W2765811365","https://openalex.org/W2766672686","https://openalex.org/W2950258612","https://openalex.org/W2963341071","https://openalex.org/W3036167779","https://openalex.org/W3080158507","https://openalex.org/W3094550259","https://openalex.org/W3094938953","https://openalex.org/W3110257065","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3131332223","https://openalex.org/W3157804362","https://openalex.org/W3160324929","https://openalex.org/W3168053944","https://openalex.org/W3172949370","https://openalex.org/W3184410885","https://openalex.org/W4200483526","https://openalex.org/W4221144097","https://openalex.org/W4232282348","https://openalex.org/W4232533539","https://openalex.org/W4281820413","https://openalex.org/W4289761690","https://openalex.org/W4297841790","https://openalex.org/W4367359628","https://openalex.org/W4372347392","https://openalex.org/W4380434618","https://openalex.org/W4384080510","https://openalex.org/W6640963894","https://openalex.org/W6712317276","https://openalex.org/W6752910514","https://openalex.org/W6779823529","https://openalex.org/W6781751280","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6786375611","https://openalex.org/W6788990321","https://openalex.org/W6798721538","https://openalex.org/W6841733230","https://openalex.org/W6846900684"],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117","https://openalex.org/W2022538999","https://openalex.org/W1955763106","https://openalex.org/W2002243964","https://openalex.org/W3090086172","https://openalex.org/W4375869276","https://openalex.org/W1603113134"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,30,33,94,130,222],"speech":[3,15,167,194],"enhancement":[4],"(SE)":[5],"is":[6,98,162,186],"to":[7,27,84,153,188,201],"eliminate":[8],"the":[9,13,28,43,61,67,75,80,88,92,101,109,119,124,142,155,159,165,178,182,193,203,208,213,232,249],"background":[10],"interference":[11],"from":[12,164],"noisy":[14,38,166],"signal.":[16],"Generative":[17],"models":[18,22,97,247],"such":[19],"as":[20,171,227],"diffusion":[21,54,82,111],"(DM)":[23],"have":[24],"been":[25],"applied":[26],"task":[29],"SE":[31,45,96,150,156,229,246],"because":[32],"better":[34,85],"generalization":[35],"in":[36,108,123,212],"unseen":[37],"scenes.":[39],"Technical":[40],"routes":[41],"for":[42,176,235],"DM-based":[44,245],"methods":[46],"can":[47,224],"be":[48,225],"summarized":[49],"into":[50],"three":[51,218],"types:":[52],"task-adapted":[53,81,110],"process":[55,83],"formulation,":[56],"generator-plus-conditioner":[57],"(GPC)":[58],"structures":[59],"and":[60,78,169,196],"multi-stage":[62,228],"frameworks.":[63],"We":[64],"focus":[65],"on":[66,231],"first":[68],"two":[69],"approaches,":[70],"which":[71,223],"are":[72,254],"constructed":[73],"under":[74,248],"GPC":[76,125,214,250],"architecture":[77],"use":[79],"deal":[86],"with":[87],"real":[89],"noise.":[90],"However,":[91],"performance":[93,204],"these":[95],"limited":[99],"by":[100,118,134,207],"following":[102],"issues:":[103],"(a)":[104],"Non-Gaussian":[105],"noise":[106,132,160,197],"estimation":[107],"process.":[112],"(b)":[113],"Conditional":[114],"domain":[115,210],"bias":[116,211],"caused":[117,133,206],"weak":[120],"conditioner":[121],"design":[122],"structure.":[126],"(c)":[127],"Large":[128],"amount":[129],"residual":[131],"unreasonable":[135],"interpolation":[136],"operations":[137],"during":[138],"inference.":[139],"To":[140],"solve":[141],"above":[143],"problems,":[144],"we":[145,216],"propose":[146],"a":[147,172,190],"noise-aware":[148],"diffusion-based":[149],"model":[151,219],"(NADiffuSE)":[152],"boost":[154],"performance,":[157],"where":[158],"representation":[161],"extracted":[163],"signal":[168],"introduced":[170],"global":[173],"conditional":[174,209],"information":[175],"estimating":[177],"non-Gaussian":[179],"components.":[180],"Furthermore,":[181],"anchor-based":[183],"inference":[184],"algorithm":[185],"employed":[187],"achieve":[189],"compromise":[191],"between":[192],"distortion":[195],"residual.":[198],"In":[199],"order":[200],"mitigate":[202],"degradation":[205],"framework,":[215],"investigate":[217],"variants,":[220],"all":[221],"viewed":[226],"based":[230],"preprocessing":[233],"networks":[234],"Mel":[236],"spectrograms.":[237],"Experimental":[238],"results":[239],"show":[240],"that":[241],"NADiffuSE":[242],"outperforms":[243],"other":[244],"infrastructure.":[251],"Audio":[252],"samples":[253],"available":[255],"at:":[256],"https://square-of-w.github.io/NADiffuSE-demo/.":[257]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}