{"id":"https://openalex.org/W4405804656","doi":"https://doi.org/10.1109/lsp.2024.3522852","title":"GALD-SE: Guided Anisotropic Lightweight Diffusion for Efficient Speech Enhancement","display_name":"GALD-SE: Guided Anisotropic Lightweight Diffusion for Efficient Speech Enhancement","publication_year":2024,"publication_date":"2024-12-26","ids":{"openalex":"https://openalex.org/W4405804656","doi":"https://doi.org/10.1109/lsp.2024.3522852"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3522852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3522852","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5007897158","display_name":"Chengzhong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengzhong Wang","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-6284-8103","affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103831061","display_name":"Jian\u2010Jun Gu","orcid":"https://orcid.org/0000-0002-9664-1915"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianjun Gu","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9664-1915","affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102802382","display_name":"Dingding Yao","orcid":"https://orcid.org/0000-0002-9610-8782"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingding Yao","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9610-8782","affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450058","display_name":"Junfeng Li","orcid":"https://orcid.org/0000-0002-6272-9169"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfeng Li","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6272-9169","affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6907-5770","affiliations":[{"raw_affiliation_string":"Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2815,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54523309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"426","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9965999722480774,"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":0.9965999722480774,"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":0.974399983882904,"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/speech-enhancement","display_name":"Speech enhancement","score":0.6626672744750977},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5930339694023132},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5750397443771362},{"id":"https://openalex.org/keywords/anisotropic-diffusion","display_name":"Anisotropic diffusion","score":0.53472501039505},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4646660089492798},{"id":"https://openalex.org/keywords/anisotropy","display_name":"Anisotropy","score":0.42028868198394775},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.19182750582695007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16384083032608032},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10698592662811279},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.0619434118270874}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6626672744750977},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5930339694023132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5750397443771362},{"id":"https://openalex.org/C203504353","wikidata":"https://www.wikidata.org/wiki/Q4765461","display_name":"Anisotropic diffusion","level":3,"score":0.53472501039505},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4646660089492798},{"id":"https://openalex.org/C85725439","wikidata":"https://www.wikidata.org/wiki/Q466686","display_name":"Anisotropy","level":2,"score":0.42028868198394775},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.19182750582695007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16384083032608032},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10698592662811279},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0619434118270874},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3522852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3522852","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5400705894","display_name":null,"funder_award_id":"12425413","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7538457160","display_name":null,"funder_award_id":"L247022","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G8717273534","display_name":null,"funder_award_id":"12104483","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1552314771","https://openalex.org/W1999846783","https://openalex.org/W2096779346","https://openalex.org/W2128653836","https://openalex.org/W2144404214","https://openalex.org/W2516001803","https://openalex.org/W2603567530","https://openalex.org/W2952218014","https://openalex.org/W2963868408","https://openalex.org/W3096408984","https://openalex.org/W3097945073","https://openalex.org/W3160085755","https://openalex.org/W3161480375","https://openalex.org/W4221143458","https://openalex.org/W4221144097","https://openalex.org/W4225905067","https://openalex.org/W4281820413","https://openalex.org/W4297841790","https://openalex.org/W4312570973","https://openalex.org/W4367281387","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W4382202691","https://openalex.org/W4384080510","https://openalex.org/W4385822788","https://openalex.org/W4385823353","https://openalex.org/W4388620484","https://openalex.org/W4392903897","https://openalex.org/W4392939451","https://openalex.org/W4399345616","https://openalex.org/W4402112093","https://openalex.org/W4402112483","https://openalex.org/W4402112506","https://openalex.org/W4402703066","https://openalex.org/W6779823529","https://openalex.org/W6786375611","https://openalex.org/W6849109464","https://openalex.org/W6853228856","https://openalex.org/W6855261814"],"related_works":["https://openalex.org/W2365492952","https://openalex.org/W1971715485","https://openalex.org/W27212783","https://openalex.org/W2112067436","https://openalex.org/W2076389328","https://openalex.org/W4206639753","https://openalex.org/W4292694493","https://openalex.org/W2135897680","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,26,75,189],"is":[2,76],"designed":[3],"to":[4,103,127],"enhance":[5],"the":[6,35,38,50,65,71,93,97,120,124,154,180,192],"intelligibility":[7],"and":[8,44,87,148,186],"quality":[9],"of":[10,22,37,89,146],"speech":[11,25,47,74,149,188],"across":[12],"diverse":[13],"noise":[14,43,85,115,147],"conditions.":[15],"Recently,":[16],"diffusion":[17,121,175],"models":[18],"have":[19],"gained":[20],"lots":[21],"attention":[23],"in":[24,96,197,206],"area,":[27],"achieving":[28],"competitive":[29],"results.":[30],"Current":[31],"diffusion-based":[32,185],"methods":[33,54],"blur":[34],"distribution":[36,48],"signal":[39],"with":[40,116,160],"isotropic":[41],"Gaussian":[42],"recover":[45],"clean":[46,94,129],"from":[49,57,70],"prior.":[51],"However,":[52],"these":[53],"often":[55],"suffer":[56],"a":[58,79,111,166],"substantial":[59],"computational":[60,66,138],"burden.":[61],"We":[62],"argue":[63],"that":[64,73,113,153,171],"inefficiency":[67],"partially":[68],"stems":[69],"oversight":[72],"not":[77,101],"purely":[78],"generative":[80],"task;":[81],"it":[82],"primarily":[83],"involves":[84],"reduction":[86],"completion":[88],"missing":[90],"information,":[91],"while":[92,140],"clues":[95,130],"original":[98],"mixture":[99],"do":[100],"need":[102],"be":[104],"regenerated.":[105],"In":[106],"this":[107],"paper,":[108],"we":[109],"propose":[110],"method":[112,156,194],"introduces":[114],"anisotropic":[117],"guidance":[118],"during":[119],"process,":[122],"allowing":[123],"neural":[125],"network":[126],"preserve":[128],"within":[131],"noisy":[132,199],"recordings.":[133],"This":[134,177],"approach":[135],"substantially":[136],"reduces":[137],"complexity":[139],"exhibiting":[141],"robustness":[142],"against":[143],"various":[144],"forms":[145],"distortion.":[150],"Experiments":[151],"demonstrate":[152],"proposed":[155,193],"achieves":[157],"state-of-the-art":[158],"results":[159],"only":[161],"approximately":[162],"4.5":[163],"million":[164],"parameters,":[165],"number":[167],"significantly":[168],"lower":[169],"than":[170],"required":[172],"by":[173],"other":[174],"methods.":[176],"effectively":[178],"narrows":[179],"model":[181],"size":[182],"disparity":[183],"between":[184],"predictive":[187],"approaches.":[190],"Additionally,":[191],"performs":[195],"well":[196],"very":[198],"scenarios,":[200],"demonstrating":[201],"its":[202],"potential":[203],"for":[204],"applications":[205],"highly":[207],"challenging":[208],"environments.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}