{"id":"https://openalex.org/W3145755240","doi":"https://doi.org/10.1109/slt48900.2021.9383622","title":"End-To-End Silent Speech Recognition with Acoustic Sensing","display_name":"End-To-End Silent Speech Recognition with Acoustic Sensing","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3145755240","doi":"https://doi.org/10.1109/slt48900.2021.9383622","mag":"3145755240"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5076982760","display_name":"Jian Luo","orcid":"https://orcid.org/0000-0002-9756-3066"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Luo","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074472751","display_name":"Jianzong Wang","orcid":"https://orcid.org/0000-0002-9237-4231"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jianzong Wang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977180","display_name":"Ning Cheng","orcid":"https://orcid.org/0000-0002-0988-5023"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Cheng","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011273813","display_name":"Guilin Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Guilin Jiang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016038454","display_name":"Jing Xiao","orcid":"https://orcid.org/0000-0001-9615-4749"},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd","institution_ids":["https://openalex.org/I4401726822"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0809,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.76226819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"606","last_page":"612"},"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":0.9980999827384949,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.796149492263794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7859271168708801},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6028062105178833},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.553189218044281},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5526337623596191},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4642198085784912},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4352433979511261},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4315638542175293},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41987723112106323},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41300058364868164},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3455837368965149},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3392403721809387},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0851045548915863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796149492263794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7859271168708801},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6028062105178833},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.553189218044281},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5526337623596191},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4642198085784912},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4352433979511261},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4315638542175293},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41987723112106323},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41300058364868164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3455837368965149},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3392403721809387},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0851045548915863},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1983171295","https://openalex.org/W1997834106","https://openalex.org/W2024681590","https://openalex.org/W2060510034","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2145442746","https://openalex.org/W2153200718","https://openalex.org/W2166243357","https://openalex.org/W2294901616","https://openalex.org/W2407080277","https://openalex.org/W2508171209","https://openalex.org/W2508345357","https://openalex.org/W2515755543","https://openalex.org/W2525860450","https://openalex.org/W2551572271","https://openalex.org/W2764166175","https://openalex.org/W2765636281","https://openalex.org/W2793257307","https://openalex.org/W2889007195","https://openalex.org/W2907493122","https://openalex.org/W2911233953","https://openalex.org/W2952746495","https://openalex.org/W2964308564","https://openalex.org/W3004196347","https://openalex.org/W4298112588","https://openalex.org/W6675365184","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6713762819","https://openalex.org/W6732872814"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2012540220","https://openalex.org/W2170116036","https://openalex.org/W2890085347","https://openalex.org/W168087846","https://openalex.org/W2118159520","https://openalex.org/W2904739811","https://openalex.org/W2429322162","https://openalex.org/W99806001","https://openalex.org/W2842698324"],"abstract_inverted_index":{"Silent":[0],"speech":[1,20],"interfaces":[2],"(SSI)":[3],"has":[4],"been":[5],"an":[6,74],"exciting":[7],"area":[8],"of":[9,41,57,98],"recent":[10],"interest.":[11],"In":[12],"this":[13],"paper,":[14],"we":[15,71],"present":[16],"a":[17,89],"non-invasive":[18],"silent":[19],"interface":[21],"that":[22],"uses":[23],"inaudible":[24],"acoustic":[25],"signals":[26,46],"to":[27,44,49,67],"capture":[28],"people's":[29],"lip":[30],"movements":[31],"when":[32],"they":[33],"speak.":[34],"We":[35],"exploit":[36],"the":[37,42,63,80],"speaker":[38],"and":[39,47,82,102,105],"microphone":[40],"smartphone":[43],"emit":[45],"listen":[48],"their":[50],"reflections,":[51],"respectively.":[52],"The":[53],"extracted":[54],"phase":[55],"features":[56],"these":[58],"reflections":[59],"are":[60],"fed":[61],"into":[62],"deep":[64],"learning":[65],"networks":[66],"recognize":[68],"speech.":[69],"And":[70],"also":[72],"propose":[73],"end-to-end":[75],"recognition":[76],"framework,":[77],"which":[78],"combines":[79],"CNN":[81],"attention-based":[83],"encoder-decoder":[84],"network.":[85],"Evaluation":[86],"results":[87],"on":[88],"limited":[90],"vocabulary":[91],"(54":[92],"sentences)":[93],"yield":[94],"word":[95],"error":[96],"rates":[97],"8.4%":[99],"in":[100],"speaker-independent":[101],"environment-independent":[103],"settings,":[104],"8.1%":[106],"for":[107],"unseen":[108],"sentence":[109],"testing.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
