{"id":"https://openalex.org/W3201134189","doi":"https://doi.org/10.1145/3478093","title":"Sensing to Hear","display_name":"Sensing to Hear","publication_year":2021,"publication_date":"2021-09-09","ids":{"openalex":"https://openalex.org/W3201134189","doi":"https://doi.org/10.1145/3478093","mag":"3201134189"},"language":"en","primary_location":{"id":"doi:10.1145/3478093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3478093","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/A5114378267","display_name":"Qian Zhang","orcid":"https://orcid.org/0000-0001-9205-1881"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qian Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391562","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0003-4872-4860"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010296816","display_name":"Run Zhao","orcid":"https://orcid.org/0000-0003-3744-6156"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Run Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080735109","display_name":"Yinggang Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinggang Yu","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090868485","display_name":"Junjie Shen","orcid":"https://orcid.org/0000-0002-8791-9049"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Shen","raw_affiliation_strings":["Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114378267"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.698,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.84890496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"5","issue":"3","first_page":"1","last_page":"30"},"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.8020123243331909},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6676933765411377},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5655354261398315},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4790676534175873},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.45334434509277344},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4529503881931305},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4506053924560547},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45047247409820557},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.4251243472099304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2974807024002075},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2828788161277771},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.19240286946296692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8020123243331909},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6676933765411377},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5655354261398315},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4790676534175873},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.45334434509277344},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4529503881931305},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4506053924560547},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45047247409820557},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.4251243472099304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2974807024002075},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2828788161277771},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19240286946296692},{"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3478093","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3478093","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G5351137422","display_name":null,"funder_award_id":"19DZ2283800","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1965248225","https://openalex.org/W1983108229","https://openalex.org/W1997834106","https://openalex.org/W2015394094","https://openalex.org/W2017475793","https://openalex.org/W2038304148","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2081144555","https://openalex.org/W2100417866","https://openalex.org/W2127851351","https://openalex.org/W2141411743","https://openalex.org/W2153200718","https://openalex.org/W2194775991","https://openalex.org/W2291877678","https://openalex.org/W2342662179","https://openalex.org/W2399593873","https://openalex.org/W2405774341","https://openalex.org/W2460742184","https://openalex.org/W2525798395","https://openalex.org/W2525860450","https://openalex.org/W2550397165","https://openalex.org/W2551572271","https://openalex.org/W2593116425","https://openalex.org/W2616400984","https://openalex.org/W2625581252","https://openalex.org/W2749588430","https://openalex.org/W2761246556","https://openalex.org/W2764166175","https://openalex.org/W2765636281","https://openalex.org/W2788241093","https://openalex.org/W2794782869","https://openalex.org/W2795038031","https://openalex.org/W2810614229","https://openalex.org/W2885724687","https://openalex.org/W2890820256","https://openalex.org/W2891312406","https://openalex.org/W2897318954","https://openalex.org/W2898050070","https://openalex.org/W2911233953","https://openalex.org/W2912868098","https://openalex.org/W2937484199","https://openalex.org/W2937525188","https://openalex.org/W2952746495","https://openalex.org/W2953231542","https://openalex.org/W2953236873","https://openalex.org/W2962866211","https://openalex.org/W2963242190","https://openalex.org/W2963840672","https://openalex.org/W2964171275","https://openalex.org/W2964204553","https://openalex.org/W2972583435","https://openalex.org/W2973223332","https://openalex.org/W2977115923","https://openalex.org/W2983800141","https://openalex.org/W2998161426","https://openalex.org/W3003850239","https://openalex.org/W3010673682","https://openalex.org/W3034763882","https://openalex.org/W3083703874","https://openalex.org/W3091905774","https://openalex.org/W3098337560","https://openalex.org/W3108244215","https://openalex.org/W3123318516","https://openalex.org/W3140645045","https://openalex.org/W3144915432","https://openalex.org/W3149794337","https://openalex.org/W3176150142","https://openalex.org/W3201613167","https://openalex.org/W3217415709","https://openalex.org/W4200482297","https://openalex.org/W4232282348","https://openalex.org/W4289665794"],"related_works":["https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2747006289","https://openalex.org/W2072884270","https://openalex.org/W4252682934","https://openalex.org/W2356426224","https://openalex.org/W2734909224","https://openalex.org/W2124849039","https://openalex.org/W2851491717","https://openalex.org/W2550583663"],"abstract_inverted_index":{"Voice":[0],"interactions":[1],"and":[2,114,155,167,207,246,257],"voice":[3,39,104,123,281],"messages":[4],"on":[5,139,184],"mobile":[6,140,280],"phones":[7,84],"are":[8,159],"rapidly":[9],"growing":[10],"in":[11,25,29,53,152,226],"popularity.":[12],"However,":[13],"the":[14,33,47,63,66,76,87,100,109,116,122,182,195,221,237,242,253,258,277],"user":[15],"experience":[16],"of":[17,65,83,95,102,111,144,223,279],"these":[18,54],"services":[19],"is":[20,74,146,191],"still":[21],"worse":[22],"than":[23],"desired":[24],"noisy":[26,217,243],"environments,":[27],"especially":[28],"multi-talker":[30],"scenarios,":[31],"where":[32],"phone":[34],"can":[35,85,234],"only":[36,44],"provide":[37],"low-quality":[38],"recordings.":[40],"Speech":[41],"enhancement":[42,138,261],"using":[43],"audio":[45,154,244],"as":[46,148],"input":[48],"remains":[49],"a":[50,129,171,187,203,273],"grand":[51],"challenge":[52],"scenarios.":[55,228],"In":[56,178],"this":[57,61],"paper,":[58],"we":[59,106,267],"handle":[60],"with":[62,252],"help":[64],"emerging":[67],"acoustic":[68,78,112,156],"sensing":[69,113,157],"technology.":[70],"The":[71,142],"key":[72],"insight":[73],"that":[75,232,269],"inaudible":[77],"signals":[79],"emitted":[80],"by":[81],"speakers":[82],"capture":[86],"subtle":[88],"lip":[89,97,118],"movements":[90],"when":[91],"people":[92],"speak.":[93],"Instead":[94],"enabling":[96],"reading":[98],"for":[99,135],"classification":[101],"limited":[103],"commands,":[105],"further":[107],"unlock":[108],"potential":[110],"leverage":[115],"captured":[117],"information":[119],"to":[120,174,180,193,197,205,219,276],"improve":[121,181],"recording":[124],"quality.":[125],"We":[126,201,210],"propose":[127],"WaveVoice,":[128],"joint":[130,172],"audio-sensory":[131],"deep":[132],"learning":[133,189],"method":[134],"end-to-end":[136],"speech":[137,240,260],"phones.":[141],"model":[143,196,256],"WaveVoice":[145,233,270],"structured":[147],"an":[149],"encoder-decoder":[150,255],"network,":[151],"which":[153],"data":[158],"processed":[160],"through":[161],"two":[162],"individual":[163],"CNN":[164],"branches,":[165],"respectively,":[166],"then":[168],"fused":[169],"into":[170],"network":[173],"generate":[175],"enhanced":[176],"speech.":[177],"addition,":[179],"performance":[183,250],"new":[185],"users,":[186],"self-supervised":[188],"methodology":[190],"developed":[192],"adapt":[194],"extract":[198],"speaker-specific":[199],"features.":[200],"construct":[202],"dataset":[204],"train":[206],"evaluate":[208],"WaveVoice.":[209],"also":[211],"perform":[212],"online":[213],"tests":[214],"under":[215],"various":[216],"conditions":[218],"show":[220,231],"applicability":[222],"our":[224],"system":[225],"real-world":[227],"Experimental":[229],"results":[230],"effectively":[235],"reconstruct":[236],"target":[238],"clean":[239],"from":[241],"signals,":[245],"yield":[247],"notably":[248],"superior":[249],"compared":[251],"audio-only":[254],"state-of-the-art":[259],"methods.":[262],"Given":[263],"its":[264],"promising":[265],"performance,":[266],"believe":[268],"has":[271],"made":[272],"substantial":[274],"contribution":[275],"advancement":[278],"input.":[282]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2021-09-27T00:00:00"}
