{"id":"https://openalex.org/W4416926492","doi":"https://doi.org/10.1145/3770672","title":"<i>mmMUSE:</i> An mmWave-based Motion-resilient Universal Speech Enhancement System","display_name":"<i>mmMUSE:</i> An mmWave-based Motion-resilient Universal Speech Enhancement System","publication_year":2025,"publication_date":"2025-12-02","ids":{"openalex":"https://openalex.org/W4416926492","doi":"https://doi.org/10.1145/3770672"},"language":"en","primary_location":{"id":"doi:10.1145/3770672","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3770672","pdf_url":null,"source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","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/A5102275613","display_name":"Wang Lingyu","orcid":"https://orcid.org/0009-0005-5524-1025"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyu Wang","raw_affiliation_strings":["University of Science and Technology of China (USTC), Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0005-5524-1025","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC), Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kai Wang","orcid":"https://orcid.org/0009-0001-8860-9042"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Wang","raw_affiliation_strings":["University of Science and Technology of China (USTC), Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0001-8860-9042","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC), Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424814","display_name":"Dequan Wang","orcid":"https://orcid.org/0000-0003-0877-4636"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dequan Wang","raw_affiliation_strings":["University of Science and Technology of China (USTC), Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-0877-4636","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC), Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111319696","display_name":"You Zuo","orcid":"https://orcid.org/0009-0004-0769-2924"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You Zuo","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China (USTC), Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0004-0769-2924","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China (USTC), Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101989063","display_name":"Chenming He","orcid":"https://orcid.org/0009-0008-2330-3799"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenming He","raw_affiliation_strings":["University of Science and Technology of China (USTC), Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0008-2330-3799","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC), Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023863179","display_name":"Chengzhen Meng","orcid":"https://orcid.org/0009-0006-4285-1905"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengzhen Meng","raw_affiliation_strings":["University of Science and Technology of China (USTC), Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0009-0006-4285-1905","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC), Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101588749","display_name":"Xiaoran Fan","orcid":"https://orcid.org/0000-0002-6368-9250"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoran Fan","raw_affiliation_strings":["Google, Mountain View, California, USA"],"raw_orcid":"https://orcid.org/0000-0002-6368-9250","affiliations":[{"raw_affiliation_string":"Google, Mountain View, California, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101524146","display_name":"Haojie Ren","orcid":"https://orcid.org/0000-0001-5741-6611"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojie Ren","raw_affiliation_strings":["School, University of Science and Technology of China (USTC), Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-5741-6611","affiliations":[{"raw_affiliation_string":"School, University of Science and Technology of China (USTC), Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103041851","display_name":"Yanyong Zhang","orcid":"https://orcid.org/0000-0001-9046-798X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyong Zhang","raw_affiliation_strings":["University of Science and Technology of China (USTC), Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-9046-798X","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China (USTC), Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.064,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82711059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"9","issue":"4","first_page":"1","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9577000141143799,"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":0.9577000141143799,"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":0.006000000052154064,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.004399999976158142,"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/speech-enhancement","display_name":"Speech enhancement","score":0.7099000215530396},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5404999852180481},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.529699981212616},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46959999203681946},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.46230000257492065},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.36390000581741333}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7099000215530396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7041000127792358},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6516000032424927},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.529699981212616},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46959999203681946},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33480000495910645},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.2896000146865845},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3770672","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3770672","pdf_url":null,"source":{"id":"https://openalex.org/S4210219751","display_name":"Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies","issn_l":"2474-9567","issn":["2474-9567"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2030878855","https://openalex.org/W2049333779","https://openalex.org/W2051057783","https://openalex.org/W2066663732","https://openalex.org/W2067295501","https://openalex.org/W2070126272","https://openalex.org/W2084511304","https://openalex.org/W2110322414","https://openalex.org/W2120847449","https://openalex.org/W2143612262","https://openalex.org/W2167583760","https://openalex.org/W2194775991","https://openalex.org/W2286130239","https://openalex.org/W2304609584","https://openalex.org/W2411057395","https://openalex.org/W2752782242","https://openalex.org/W2884585870","https://openalex.org/W2897318954","https://openalex.org/W2937484199","https://openalex.org/W2943554574","https://openalex.org/W2953297989","https://openalex.org/W2962866211","https://openalex.org/W2962935966","https://openalex.org/W2964058413","https://openalex.org/W2998161426","https://openalex.org/W3088639796","https://openalex.org/W3109009614","https://openalex.org/W3140645045","https://openalex.org/W3213319487","https://openalex.org/W4285297780","https://openalex.org/W4294892047","https://openalex.org/W4306250185","https://openalex.org/W4322731291","https://openalex.org/W4372260610","https://openalex.org/W4380928279","https://openalex.org/W4385965602","https://openalex.org/W4387212628","https://openalex.org/W4387212631","https://openalex.org/W4388706355","https://openalex.org/W4392823854","https://openalex.org/W4393290239","https://openalex.org/W4395447416","https://openalex.org/W4396241200","https://openalex.org/W4396843730","https://openalex.org/W4402349786","https://openalex.org/W4402349817","https://openalex.org/W4402916681","https://openalex.org/W4404586145","https://openalex.org/W4405014543","https://openalex.org/W4405022676"],"related_works":[],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,51,132],"improves":[2],"the":[3,75,80,83,129],"user":[4],"interaction":[5],"experience":[6],"in":[7,136,140,159,175],"voice-based":[8],"smart":[9],"systems.":[10],"While":[11],"microphone-based":[12],"speech":[13,50,118,131],"perception":[14],"is":[15,21],"limited":[16],"by":[17,73,134],"airborne":[18],"noise,":[19,164],"mmWave":[20,55],"immune":[22],"to":[23,78,119],"such":[24],"interference.":[25],"However,":[26],"user-device":[27],"motion":[28,60],"hinders":[29],"mmWave-based":[30,47],"vocal":[31,34,69,84],"extraction,":[32],"dispersing":[33],"signals":[35],"and":[36,56,107,115,138,156,169,182],"introducing":[37],"distortions.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42,62,86],"propose":[43,63],"mmMUSE":[44,127,184],",":[45],"an":[46,100],"motion-resilient":[48],"universal":[49],"system":[52],"that":[53,98],"integrates":[54],"audio.":[57],"To":[58],"mitigate":[59],"interference,":[61],"a":[64,95,108],"two-stage":[65],"method":[66],"for":[67,104,112],"robust":[68],"vibration":[70],"extraction.":[71],"Moreover,":[72],"proposing":[74],"Vocal-Noise-Ratio":[76],"metric":[77],"assess":[79],"prominence":[81],"of":[82,117,149],"vibration,":[85],"enable":[87],"real-time":[88],"voice":[89],"activity":[90],"detection.":[91],"We":[92],"also":[93,145],"design":[94],"complex-valued":[96],"network":[97,103,111],"includes":[99],"attention-based":[101],"fusion":[102],"cross-modal":[105],"complementing":[106],"time-frequency":[109],"masking":[110],"correcting":[113],"amplitude":[114],"phase":[116],"isolate":[120],"noises.":[121],"Using":[122],"datasets":[123],"from":[124],"46":[125],"participants,":[126],"outperforms":[128],"state-of-the-art":[130],"models":[133],"26%":[135],"SISDR":[137,147],"34%":[139],"STOI":[141],"on":[142],"average.":[143],"It":[144],"achieves":[146,185],"improvements":[148],"16.72":[150],"dB,":[151,153,155],"17.93":[152],"14.93":[154],"18.95":[157],"dB":[158],"controlled":[160],"environments":[161],"involving":[162],"intense":[163],"extensive":[165],"motion,":[166],"multiple":[167],"speakers,":[168],"various":[170],"obstructive":[171],"materials,":[172],"respectively.":[173],"Finally,":[174],"real-world":[176],"scenarios,":[177],"including":[178],"running,":[179],"public":[180],"spaces,":[181],"driving,":[183],"WER":[186],"below":[187],"10%.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-02T00:00:00"}
