{"id":"https://openalex.org/W4386242195","doi":"https://doi.org/10.1109/infocom53939.2023.10229085","title":"mmMIC: Multi-modal Speech Recognition based on mmWave Radar","display_name":"mmMIC: Multi-modal Speech Recognition based on mmWave Radar","publication_year":2023,"publication_date":"2023-05-17","ids":{"openalex":"https://openalex.org/W4386242195","doi":"https://doi.org/10.1109/infocom53939.2023.10229085"},"language":"en","primary_location":{"id":"doi:10.1109/infocom53939.2023.10229085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom53939.2023.10229085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2023 - IEEE Conference on Computer Communications","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/A5100948487","display_name":"Long Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Long Fan","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365442","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0002-2994-6743"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103780167","display_name":"Xinran Lu","orcid":"https://orcid.org/0000-0002-8172-6860"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinran Lu","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100421757","display_name":"Yi Li","orcid":"https://orcid.org/0000-0003-2304-5802"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Li","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065806203","display_name":"Chuyu Wang","orcid":"https://orcid.org/0000-0002-1479-9023"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuyu Wang","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043533769","display_name":"Sanglu Lu","orcid":"https://orcid.org/0000-0003-1467-4519"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanglu Lu","raw_affiliation_strings":["Nanjing University,State Key Laboratory for Novel Software Technology,China","State Key Laboratory for Novel Software Technology, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University,State Key Laboratory for Novel Software Technology,China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100948487"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":6.2657,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.97527048,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9977999925613403,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.7418721914291382},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6168740391731262},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6139528751373291},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5520581603050232},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4940526783466339},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4900554418563843},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42975395917892456},{"id":"https://openalex.org/keywords/vibration","display_name":"Vibration","score":0.4134160876274109},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3975295126438141},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2907428741455078},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1046166718006134}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7418721914291382},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6168740391731262},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6139528751373291},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5520581603050232},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4940526783466339},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4900554418563843},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42975395917892456},{"id":"https://openalex.org/C198394728","wikidata":"https://www.wikidata.org/wiki/Q3695508","display_name":"Vibration","level":2,"score":0.4134160876274109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3975295126438141},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2907428741455078},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1046166718006134},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom53939.2023.10229085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom53939.2023.10229085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2023 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5899999737739563}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1977985044","https://openalex.org/W2046128267","https://openalex.org/W2090479364","https://openalex.org/W2120847449","https://openalex.org/W2485020921","https://openalex.org/W2611961900","https://openalex.org/W2792051659","https://openalex.org/W2919076405","https://openalex.org/W2936078256","https://openalex.org/W2944172587","https://openalex.org/W2962793481","https://openalex.org/W2980617023","https://openalex.org/W2996463502","https://openalex.org/W3015383493","https://openalex.org/W3015834770","https://openalex.org/W3015841457","https://openalex.org/W3015958938","https://openalex.org/W3087859191","https://openalex.org/W3094502228","https://openalex.org/W3109009614","https://openalex.org/W3140645045","https://openalex.org/W3161697668","https://openalex.org/W3172125635","https://openalex.org/W3172863135","https://openalex.org/W3184369217","https://openalex.org/W3212869614","https://openalex.org/W3213319487","https://openalex.org/W4200196915","https://openalex.org/W4200264829","https://openalex.org/W4225540200","https://openalex.org/W4283216570","https://openalex.org/W4283218709","https://openalex.org/W4283219755","https://openalex.org/W4283220806","https://openalex.org/W4312784228","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2357191878","https://openalex.org/W1997078944","https://openalex.org/W1968065688","https://openalex.org/W1552846815","https://openalex.org/W2142945567","https://openalex.org/W4289829835","https://openalex.org/W2030332364","https://openalex.org/W2005459225","https://openalex.org/W4220830676","https://openalex.org/W1670456569"],"abstract_inverted_index":{"With":[0],"the":[1,16,40,52,62,80,125,135,145,154],"proliferation":[2],"of":[3,18,42,65,75,98],"voice":[4],"assistants,":[5],"microphone-based":[6],"speech":[7,36,92,121,156],"recognition":[8,37,122,157],"technology":[9],"usually":[10],"cannot":[11],"achieve":[12],"good":[13],"performance":[14,146],"in":[15,147,161],"situation":[17],"multiple":[19,43],"sound":[20,44],"sources":[21,45],"and":[22,46,58,86,101,131,143],"ambient":[23,47],"noises.":[24],"In":[25],"this":[26],"paper,":[27],"we":[28],"propose":[29,68,90,115],"a":[30,69,91,116,140],"novel":[31],"mmWave-based":[32],"solution":[33],"to":[34,38,78,106],"perform":[35],"tackle":[39],"issues":[41],"noises,":[48],"by":[49,123],"precisely":[50],"extracting":[51],"multi-modal":[53,117],"features":[54,127],"from":[55,61,83,128],"lip":[56,76,99,129],"motion":[57,77,85,100,130],"vocal-cords":[59,102,132],"vibration":[60,103,133],"single":[63],"channel":[64],"mmWave.":[66],"We":[67,89,114,138],"difference-based":[70],"method":[71,94],"for":[72,120],"feature":[73],"extraction":[74],"suppress":[79],"dynamic":[81],"interference":[82],"body":[84],"head":[87],"motion.":[88],"detection":[93],"based":[95],"on":[96,111],"cross-validation":[97],"so":[104],"as":[105],"avoid":[107],"wasting":[108],"computing":[109],"resources":[110],"nonspeaking":[112],"activities.":[113],"fusion":[118],"framework":[119],"fusing":[124],"signal":[126],"with":[134],"attention":[136],"mechanism.":[137],"implemented":[139],"prototype":[141],"system":[142],"evaluated":[144],"real":[148],"test-beds.":[149],"Experiment":[150],"results":[151],"show":[152],"that":[153],"average":[155],"accuracy":[158],"is":[159],"92.8%":[160],"realistic":[162],"environments.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
