{"id":"https://openalex.org/W4412446714","doi":"https://doi.org/10.1109/dsp65409.2025.11075136","title":"Graph-Guided Spatial-Temporal Diffusion Model for Speech Enhancement with Microphone Array","display_name":"Graph-Guided Spatial-Temporal Diffusion Model for Speech Enhancement with Microphone Array","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4412446714","doi":"https://doi.org/10.1109/dsp65409.2025.11075136"},"language":"en","primary_location":{"id":"doi:10.1109/dsp65409.2025.11075136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsp65409.2025.11075136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 25th International Conference on Digital Signal Processing (DSP)","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/A5083821461","display_name":"Jingjing Yu","orcid":"https://orcid.org/0000-0002-1491-0377"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Yu","raw_affiliation_strings":["School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113982346","display_name":"Lirui Wu","orcid":"https://orcid.org/0009-0008-9052-8795"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirui Wu","raw_affiliation_strings":["School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012434366","display_name":"Chi Yang","orcid":"https://orcid.org/0009-0002-4682-4008"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Yang","raw_affiliation_strings":["School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100656536","display_name":"Ranran Liu","orcid":"https://orcid.org/0000-0002-3323-1521"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ranran Liu","raw_affiliation_strings":["School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003112254","display_name":"A. Manikas","orcid":"https://orcid.org/0000-0001-6905-3280"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Athanassios Manikas","raw_affiliation_strings":["Imperial College London,Department of Electrical and Electronic Engineering,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,London,UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1842739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9865999817848206,"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":0.9865999817848206,"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":0.7126207947731018},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6709058284759521},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5501018762588501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5244674682617188},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.4567303955554962},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.45665255188941956},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4458162784576416},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.42242926359176636},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2146565318107605},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.12063717842102051},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12046578526496887},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.08520713448524475},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06468135118484497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7126207947731018},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6709058284759521},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5501018762588501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5244674682617188},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.4567303955554962},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.45665255188941956},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4458162784576416},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.42242926359176636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2146565318107605},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.12063717842102051},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12046578526496887},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.08520713448524475},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06468135118484497},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsp65409.2025.11075136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsp65409.2025.11075136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 25th International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2003399270","https://openalex.org/W2052666245","https://openalex.org/W2053917597","https://openalex.org/W2094721231","https://openalex.org/W2141998673","https://openalex.org/W2168379380","https://openalex.org/W2889442120","https://openalex.org/W2898268964","https://openalex.org/W3083423753","https://openalex.org/W3163591408","https://openalex.org/W4205689591","https://openalex.org/W4221144097","https://openalex.org/W4224931298","https://openalex.org/W4225905067","https://openalex.org/W4280569506","https://openalex.org/W4375869120","https://openalex.org/W4380434618","https://openalex.org/W4385822710","https://openalex.org/W4390045359","https://openalex.org/W4392909903","https://openalex.org/W4402352211","https://openalex.org/W4407450948","https://openalex.org/W4407783183","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6783713337","https://openalex.org/W6795288823","https://openalex.org/W6810523761","https://openalex.org/W6842958722","https://openalex.org/W6871468213"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2380771148","https://openalex.org/W2900122540","https://openalex.org/W2396048001","https://openalex.org/W4408354526","https://openalex.org/W4240587264","https://openalex.org/W2348931051"],"abstract_inverted_index":{"Generative":[0],"diffusion":[1,67,79,100,130],"models":[2],"have":[3],"emerged":[4],"as":[5],"promising":[6],"solutions":[7],"for":[8,53,103],"speech":[9],"enhancement":[10],"(SE),":[11],"particularly":[12],"in":[13,89],"unlabeled":[14],"and":[15,47,137,148],"unseen":[16,149],"noisy":[17],"scenarios.":[18],"However,":[19],"their":[20],"real-world":[21],"deployment":[22],"faces":[23],"three":[24],"fundamental":[25],"challenges:":[26],"limited":[27],"generalization":[28,126],"to":[29,85],"complex":[30],"dynamic":[31,121],"noise":[32,122,150],"conditions":[33],"beyond":[34],"training":[35],"distributions,":[36],"excessive":[37],"computational":[38],"demands":[39],"from":[40],"iterative":[41],"sampling":[42,101],"that":[43,69],"hinder":[44],"real-time":[45],"implementation,":[46],"dependence":[48],"on":[49],"large-scale":[50],"paired":[51],"data":[52],"optimal":[54],"performance.":[55],"To":[56],"address":[57],"these":[58],"challenges,":[59],"we":[60],"propose":[61],"G-DiffuMSE":[62],"-":[63],"a":[64],"novel":[65],"graph-guided":[66],"framework":[68,133],"integrates":[70],"multidimensional":[71],"spatial-temporal":[72],"graph":[73],"convolutional":[74],"networks":[75],"(STGCN)":[76],"with":[77],"conditional":[78],"processes.":[80],"Leveraging":[81],"its":[82],"inherent":[83],"ability":[84],"capture":[86],"spatiotemporal":[87],"correlations":[88],"multichannel":[90],"signals,":[91],"STGCN":[92],"reconstructs":[93],"the":[94,99,125],"target":[95],"structural":[96],"information,":[97],"guiding":[98],"process":[102],"more":[104],"efficient":[105],"denoising.":[106],"Additionally,":[107],"attention-based":[108],"noise-conditional":[109],"scenery":[110],"modeling,":[111],"applied":[112],"through":[113],"scene":[114],"graphs,":[115],"enhances":[116],"robustness":[117,139],"against":[118],"un-seen":[119],"or":[120],"conditions,":[123],"mitigating":[124],"limitations":[127],"of":[128],"conventional":[129],"models.":[131],"Our":[132],"demonstrates":[134],"superior":[135],"performance":[136],"strong":[138],"across":[140],"various":[141],"challenging":[142],"scenarios,":[143],"effectively":[144],"handling":[145],"both":[146],"seen":[147],"environments.":[151]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
