{"id":"https://openalex.org/W4416250360","doi":"https://doi.org/10.1109/waspaa66052.2025.11230972","title":"Distributed Asynchronous Device Speech Enhancement via Windowed Cross-Attention","display_name":"Distributed Asynchronous Device Speech Enhancement via Windowed Cross-Attention","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250360","doi":"https://doi.org/10.1109/waspaa66052.2025.11230972"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-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/A5085238281","display_name":"Gene-Ping Yang","orcid":"https://orcid.org/0000-0002-3786-3251"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Gene-Ping Yang","raw_affiliation_strings":["University of Edinburgh,CSTR"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh,CSTR","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055277441","display_name":"Sebastian Braun","orcid":"https://orcid.org/0000-0001-9060-223X"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sebastian Braun","raw_affiliation_strings":["Microsoft Research,Redmond"],"affiliations":[{"raw_affiliation_string":"Microsoft Research,Redmond","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085238281"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45205479,"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":0.9732000231742859,"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":0.9732000231742859,"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":0.0066999997943639755,"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"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.004800000227987766,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7777000069618225},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.640500009059906},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6105999946594238},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5964999794960022},{"id":"https://openalex.org/keywords/noise-canceling-microphone","display_name":"Noise-canceling microphone","score":0.4041999876499176},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3946000039577484},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.387800008058548}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7777000069618225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281000018119812},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.640500009059906},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6105999946594238},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5964999794960022},{"id":"https://openalex.org/C36922181","wikidata":"https://www.wikidata.org/wiki/Q7047650","display_name":"Noise-canceling microphone","level":5,"score":0.4041999876499176},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39980000257492065},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2978000044822693},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1973787919","https://openalex.org/W1999214619","https://openalex.org/W2066218102","https://openalex.org/W2092463830","https://openalex.org/W2098434929","https://openalex.org/W2101609516","https://openalex.org/W2117678320","https://openalex.org/W2164809687","https://openalex.org/W2168729028","https://openalex.org/W2286130239","https://openalex.org/W2294088583","https://openalex.org/W2568308529","https://openalex.org/W2568728275","https://openalex.org/W2576520820","https://openalex.org/W2617566018","https://openalex.org/W2775641139","https://openalex.org/W2892163332","https://openalex.org/W2899955959","https://openalex.org/W2964391865","https://openalex.org/W3004309045","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3110405100","https://openalex.org/W3132229649","https://openalex.org/W3133848124","https://openalex.org/W3135596623","https://openalex.org/W3160129476","https://openalex.org/W3191448984","https://openalex.org/W3198127178","https://openalex.org/W3207360934","https://openalex.org/W3215881519","https://openalex.org/W4221158617","https://openalex.org/W4225302959","https://openalex.org/W4286896457","https://openalex.org/W4311186284","https://openalex.org/W4372260070","https://openalex.org/W4385823410","https://openalex.org/W4392908343","https://openalex.org/W4402111684","https://openalex.org/W4402112373","https://openalex.org/W4408353835"],"related_works":[],"abstract_inverted_index":{"The":[0],"increasing":[1],"number":[2,96],"of":[3,79,97,134,160],"microphone-equipped":[4],"personal":[5],"devices":[6],"offers":[7],"great":[8],"flexibility":[9],"and":[10,45,94,99,131,148,154],"potential":[11],"using":[12],"them":[13],"as":[14],"ad-hoc":[15],"microphone":[16,30,167],"arrays":[17],"in":[18,38,66,121],"dynamic":[19],"meeting":[20,40],"environments.":[21,116],"However,":[22],"most":[23],"existing":[24,105],"approaches":[25],"are":[26],"designed":[27],"for":[28,61,114,165],"time-synchronized":[29],"setups,":[31],"a":[32,58,74,122],"condition":[33],"that":[34,140],"may":[35],"not":[36],"hold":[37],"real-world":[39],"scenarios,":[41],"where":[42],"time":[43,129],"latency":[44,130],"clock":[46,132],"drift":[47,133],"vary":[48],"across":[49],"devices.":[50],"Under":[51],"such":[52],"conditions,":[53],"we":[54,72,108],"found":[55],"transform-average-concatenate":[56],"(TAC),":[57],"popular":[59],"module":[60,77,87,164],"neural":[62],"multi-microphone":[63,123],"processing,":[64],"insufficient":[65],"handling":[67],"time-asynchronous":[68],"microphones.":[69,85],"In":[70],"response,":[71],"propose":[73,109],"windowed":[75,162],"cross-attention":[76,163],"capable":[78],"dynamically":[80],"aligning":[81],"features":[82],"between":[83],"all":[84],"This":[86],"is":[88],"invariant":[89],"to":[90],"both":[91,146],"the":[92,95,158,161],"permutation":[93],"microphones":[98],"can":[100],"be":[101],"easily":[102],"integrated":[103],"into":[104],"models.":[106],"Furthermore,":[107],"an":[110],"optimal":[111],"training":[112],"target":[113],"multi-talker":[115],"We":[117],"evaluated":[118],"our":[119,141],"approach":[120],"noisy":[124],"reverberant":[125],"setup":[126],"with":[127],"unknown":[128],"each":[135],"microphone.":[136],"Experimental":[137],"results":[138],"show":[139],"method":[142],"outperforms":[143],"TAC":[144],"on":[145],"iFaSNet":[147],"CRUSE":[149],"models,":[150],"offering":[151],"faster":[152],"convergence":[153],"improved":[155],"learning,":[156],"demonstrating":[157],"efficacy":[159],"asynchronous":[166],"setups.":[168]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}
