{"id":"https://openalex.org/W3144915432","doi":"https://doi.org/10.1145/3448087","title":"SoundLip","display_name":"SoundLip","publication_year":2021,"publication_date":"2021-03-19","ids":{"openalex":"https://openalex.org/W3144915432","doi":"https://doi.org/10.1145/3448087","mag":"3144915432"},"language":"en","primary_location":{"id":"doi:10.1145/3448087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448087","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/A5100776551","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-9396-0398"},"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":"last","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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114378267"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.9329,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.91608064,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"5","issue":"1","first_page":"1","last_page":"28"},"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":0.9987000226974487,"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":0.9969000220298767,"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":0.8252442479133606},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6806348562240601},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6358197331428528},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6223333477973938},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.46907681226730347},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.464912474155426},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.45735660195350647},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44129982590675354},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.43790215253829956},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42790278792381287},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4244665205478668},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3716418147087097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34662145376205444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8252442479133606},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6806348562240601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6358197331428528},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6223333477973938},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.46907681226730347},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.464912474155426},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.45735660195350647},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44129982590675354},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.43790215253829956},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42790278792381287},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4244665205478668},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3716418147087097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34662145376205444},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3448087","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3448087","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W271608952","https://openalex.org/W1583837637","https://openalex.org/W1686810756","https://openalex.org/W1904948456","https://openalex.org/W1997834106","https://openalex.org/W2008120082","https://openalex.org/W2017475793","https://openalex.org/W2051626970","https://openalex.org/W2076676508","https://openalex.org/W2127141656","https://openalex.org/W2148463593","https://openalex.org/W2153200718","https://openalex.org/W2165158100","https://openalex.org/W2183341477","https://openalex.org/W2187089797","https://openalex.org/W2307299445","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2419247625","https://openalex.org/W2468875367","https://openalex.org/W2508345357","https://openalex.org/W2525798395","https://openalex.org/W2551572271","https://openalex.org/W2625325839","https://openalex.org/W2761246556","https://openalex.org/W2764166175","https://openalex.org/W2765636281","https://openalex.org/W2768153200","https://openalex.org/W2793257307","https://openalex.org/W2795038031","https://openalex.org/W2889007195","https://openalex.org/W2896622783","https://openalex.org/W2897106987","https://openalex.org/W2897268228","https://openalex.org/W2897318954","https://openalex.org/W2898050070","https://openalex.org/W2907493122","https://openalex.org/W2911233953","https://openalex.org/W2912868098","https://openalex.org/W2927635891","https://openalex.org/W2936774411","https://openalex.org/W2941048526","https://openalex.org/W2949888546","https://openalex.org/W2950577311","https://openalex.org/W2952746495","https://openalex.org/W2953236873","https://openalex.org/W2953297989","https://openalex.org/W2963840672","https://openalex.org/W2972583435","https://openalex.org/W2977115923","https://openalex.org/W2979507566","https://openalex.org/W2980498517","https://openalex.org/W2980880049","https://openalex.org/W2983800141","https://openalex.org/W3003850239","https://openalex.org/W3004196347","https://openalex.org/W3010673682","https://openalex.org/W3022458451","https://openalex.org/W3103203826","https://openalex.org/W3217415709"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"As":[0],"a":[1,86,152,177,216,243],"natural":[2],"and":[3,19,30,90,108,123,132,146,186,200,215,227,234],"convenient":[4],"interaction":[5,46],"modality,":[6],"voice":[7,23,57,251],"input":[8,24,252],"has":[9,241],"now":[10],"become":[11],"indispensable":[12],"to":[13,50,63,68,128,134,140,158,181,246],"smart":[14,20,53,126],"devices":[15,54,127],"(e.g.":[16],"mobile":[17],"phones":[18],"appliances).":[21],"However,":[22],"is":[25,62],"strongly":[26],"constrained":[27],"by":[28],"surroundings":[29],"may":[31],"raise":[32],"privacy":[33],"leakage":[34],"in":[35,189,224],"public":[36],"areas.":[37],"In":[38,97,138],"this":[39],"paper,":[40],"we":[41,150,175,237],"present":[42],"SoundLip,":[43],"an":[44,190,209],"end-to-end":[45,191],"system":[47,101,207],"enabling":[48],"users":[49,74],"interact":[51],"with":[52],"via":[55],"silent":[56,250],"input.":[58],"The":[59],"key":[60],"insight":[61],"use":[64],"inaudible":[65],"acoustic":[66,130,148],"signals":[67,131],"capture":[69],"the":[70,120,161,172,247],"lip":[71,83,103],"movements":[72],"of":[73,125,211,220,249],"when":[75],"they":[76],"issue":[77],"commands.":[78,169],"Previous":[79],"works":[80],"have":[81],"considered":[82],"reading":[84,104],"as":[85,160,163,165],"naive":[87],"classification":[88],"task":[89],"thus":[91],"can":[92],"only":[93],"recognize":[94,166],"individual":[95,167,198],"words.":[96],"contrast,":[98],"our":[99],"proposed":[100],"enables":[102],"at":[105,213,222],"both":[106,225],"word":[107,168,217],"sentence":[109],"levels,":[110],"which":[111],"are":[112],"more":[113],"suitable":[114],"for":[115,171],"daily-life":[116],"use.":[117],"We":[118,193],"exploit":[119,176],"built-in":[121],"speakers":[122],"microphones":[124],"emit":[129],"listen":[133],"their":[135],"reflections,":[136],"respectively.":[137],"order":[139],"better":[141],"abstract":[142],"representations":[143],"from":[144,203],"multi-frequency":[145],"multi-modality":[147],"signals,":[149],"elaborate":[151],"hierarchical":[153],"convolutional":[154],"neural":[155],"network":[156,180],"(HCNN)":[157],"serve":[159],"front-end":[162],"well":[164],"Then,":[170],"sentence-level":[173,223],"recognition,":[174],"multi-task":[178],"encoder-decoder":[179],"get":[182],"around":[183],"temporal":[184],"segmentation":[185],"output":[187],"sentences":[188,202],"way.":[192],"evaluate":[194],"SoundLip":[195,240],"on":[196],"20":[197],"words":[199],"70":[201],"12":[204],"participants.":[205],"Our":[206],"achieves":[208],"accuracy":[210],"91.2%":[212],"word-level":[214],"error":[218],"rate":[219],"7.1%":[221],"user-independent":[226],"environment-independent":[228],"settings.":[229],"Given":[230],"its":[231],"innovative":[232],"solution":[233],"promising":[235],"performance,":[236],"believe":[238],"that":[239],"made":[242],"significant":[244],"contribution":[245],"advancement":[248],"technology.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2021-04-13T00:00:00"}