{"id":"https://openalex.org/W4377028705","doi":"https://doi.org/10.1145/3597457","title":"Wavoice: An mmWave-Assisted Noise-Resistant Speech Recognition System","display_name":"Wavoice: An mmWave-Assisted Noise-Resistant Speech Recognition System","publication_year":2023,"publication_date":"2023-05-18","ids":{"openalex":"https://openalex.org/W4377028705","doi":"https://doi.org/10.1145/3597457"},"language":"en","primary_location":{"id":"doi:10.1145/3597457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597457","pdf_url":null,"source":{"id":"https://openalex.org/S170502224","display_name":"ACM Transactions on Sensor Networks","issn_l":"1550-4859","issn":["1550-4859","1550-4867"],"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":"ACM Transactions on Sensor Networks","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/A5100381088","display_name":"Tiantian Liu","orcid":"https://orcid.org/0000-0002-4706-8817"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tiantian Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407094","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0003-0906-445X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016863481","display_name":"Zhengxiong Li","orcid":null},"institutions":[{"id":"https://openalex.org/I921990950","display_name":"University of Colorado Denver","ror":"https://ror.org/02hh7en24","country_code":"US","type":"education","lineage":["https://openalex.org/I921990950"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengxiong Li","raw_affiliation_strings":["University of Colorado Denver, Denver, United States"],"affiliations":[{"raw_affiliation_string":"University of Colorado Denver, Denver, United States","institution_ids":["https://openalex.org/I921990950"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020169895","display_name":"Ming-Chun Huang","orcid":"https://orcid.org/0000-0002-2269-4694"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Chun Huang","raw_affiliation_strings":["Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035679293","display_name":"Wenyao Xu","orcid":"https://orcid.org/0000-0001-6444-9411"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenyao Xu","raw_affiliation_strings":["University at Buffalo, the State University of New York, Buffalo, NY"],"affiliations":[{"raw_affiliation_string":"University at Buffalo, the State University of New York, Buffalo, NY","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078406349","display_name":"Feng Lin","orcid":"https://orcid.org/0000-0001-5240-5200"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Lin","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100381088"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.7924,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69950403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"20","issue":"4","first_page":"1","last_page":"29"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T13289","display_name":"Infant Health and Development","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7935178279876709},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6023967266082764},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5652698874473572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2709674835205078}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7935178279876709},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6023967266082764},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5652698874473572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2709674835205078},{"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:10.1145/3597457","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3597457","pdf_url":null,"source":{"id":"https://openalex.org/S170502224","display_name":"ACM Transactions on Sensor Networks","issn_l":"1550-4859","issn":["1550-4859","1550-4867"],"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":"ACM Transactions on Sensor Networks","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W79317937","https://openalex.org/W1631909651","https://openalex.org/W2010189898","https://openalex.org/W2057243093","https://openalex.org/W2061678360","https://openalex.org/W2104717865","https://openalex.org/W2110322414","https://openalex.org/W2129120544","https://openalex.org/W2138194976","https://openalex.org/W2156279557","https://openalex.org/W2156775872","https://openalex.org/W2158409990","https://openalex.org/W2172294905","https://openalex.org/W2213420530","https://openalex.org/W2242685705","https://openalex.org/W2327501763","https://openalex.org/W2344757691","https://openalex.org/W2496632708","https://openalex.org/W2559655401","https://openalex.org/W2600556233","https://openalex.org/W2612690371","https://openalex.org/W2750499125","https://openalex.org/W2752782242","https://openalex.org/W2762561030","https://openalex.org/W2793044632","https://openalex.org/W2797090057","https://openalex.org/W2797583228","https://openalex.org/W2866634454","https://openalex.org/W2884797218","https://openalex.org/W2897132279","https://openalex.org/W2900292050","https://openalex.org/W2914783728","https://openalex.org/W2916024349","https://openalex.org/W2932030740","https://openalex.org/W2943554574","https://openalex.org/W2953190524","https://openalex.org/W2953297989","https://openalex.org/W2962920357","https://openalex.org/W2963321191","https://openalex.org/W2964539095","https://openalex.org/W2973616902","https://openalex.org/W2990138404","https://openalex.org/W2998161426","https://openalex.org/W3006643904","https://openalex.org/W3009950332","https://openalex.org/W3012776202","https://openalex.org/W3015679345","https://openalex.org/W3016400019","https://openalex.org/W3018353706","https://openalex.org/W3018805456","https://openalex.org/W3019180776","https://openalex.org/W3021151406","https://openalex.org/W3034366997","https://openalex.org/W3088639796","https://openalex.org/W3109009614","https://openalex.org/W3109228974","https://openalex.org/W3109995084","https://openalex.org/W3131937470","https://openalex.org/W3136499730","https://openalex.org/W3137420496","https://openalex.org/W3138807202","https://openalex.org/W3140645045","https://openalex.org/W3160417706","https://openalex.org/W3213319487","https://openalex.org/W4200317075","https://openalex.org/W4226050909","https://openalex.org/W4232841423","https://openalex.org/W4253928870","https://openalex.org/W4283211061","https://openalex.org/W4283219755","https://openalex.org/W4284881846","https://openalex.org/W4284888342","https://openalex.org/W4288057735","https://openalex.org/W4288558760","https://openalex.org/W4291318484","https://openalex.org/W4300824008","https://openalex.org/W4302446929","https://openalex.org/W4302765731","https://openalex.org/W4306179797","https://openalex.org/W4384948669","https://openalex.org/W6603280604"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"As":[0],"automatic":[1],"speech":[2,68,137,174],"recognition":[3,69,152,175],"evolves,":[4],"deployment":[5],"of":[6,48,144,160,165],"the":[7,17,20,35,46,64,94,107,131,142,150],"voice":[8,110],"user":[9,114],"interface":[10],"(VUI)":[11],"has":[12,22],"boomingly":[13],"expanded.":[14],"Especially":[15],"since":[16],"COVID-19":[18],"pandemic,":[19],"VUI":[21,36],"gained":[23],"more":[24],"attention":[25],"in":[26,41,157],"online":[27],"communication":[28],"owing":[29],"to":[30,38,45,92,135],"its":[31],"non-contact":[32],"property.":[33],"However,":[34],"struggles":[37],"be":[39],"applied":[40],"public":[42],"scenes":[43],"due":[44],"degradation":[47],"received":[49],"audio":[50,82,100],"signals":[51,80,83],"caused":[52],"by":[53],"various":[54],"ambient":[55],"noises.":[56],"In":[57,163],"this":[58],"article,":[59],"we":[60,120],"propose":[61],"Wavoice":[62,105,145,169],",":[63],"first":[65],"noise-resistant":[66,109],"multi-modal":[67,127],"system":[70],"that":[71],"fuses":[72],"two":[73,123],"distinct":[74],"voices":[75],"sensing":[76],"modalities":[77],"(i.e.,":[78],"millimeter-wave":[79,98],"and":[81,99,113,167,181],"from":[84,116],"a":[85,158],"microphone)":[86],"together.":[87],"One":[88],"key":[89],"contribution":[90],"is":[91],"model":[93],"inherent":[95],"correlation":[96],"between":[97],"signals.":[101],"Based":[102],"on":[103,122],"it,":[104],"facilitates":[106],"real-time":[108],"activity":[111],"detection":[112],"targeting":[115],"multiple":[117],"speakers.":[118],"Additionally,":[119],"elaborate":[121],"novel":[124],"modules":[125],"for":[126],"fusion":[128],"embedded":[129],"into":[130],"neural":[132],"network,":[133],"leading":[134],"accurate":[136],"recognition.":[138],"Extensive":[139],"experiments":[140],"prove":[141],"effectiveness":[143],"under":[146],"adverse":[147],"conditions\u2014that":[148],"is,":[149],"character":[151,179],"error":[153,180,183],"rate":[154],"below":[155],"1%":[156],"range":[159],"7":[161],"m.":[162],"terms":[164],"robustness":[166],"accuracy,":[168],"considerably":[170],"outperforms":[171],"existing":[172],"audio-only":[173],"methods":[176],"with":[177],"lower":[178],"word":[182],"rates.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}