{"id":"https://openalex.org/W2961308210","doi":"https://doi.org/10.1109/fg.2019.8756549","title":"Are You Speaking: Real-Time Speech Activity Detection via Landmark Pooling Network","display_name":"Are You Speaking: Real-Time Speech Activity Detection via Landmark Pooling Network","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2961308210","doi":"https://doi.org/10.1109/fg.2019.8756549","mag":"2961308210"},"language":"en","primary_location":{"id":"doi:10.1109/fg.2019.8756549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg.2019.8756549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100383960","display_name":"Boyu Wang","orcid":"https://orcid.org/0000-0003-2075-3731"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boyu Wang","raw_affiliation_strings":["Computer Science Department, Stony Brook University, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stony Brook University, NY, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100424254","display_name":"Xiaolong Wang","orcid":"https://orcid.org/0000-0001-9003-4252"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaolong Wang","raw_affiliation_strings":["IBM, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, CA, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"1","last_page":"5"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9983999729156494,"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":0.864493191242218},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.7729955315589905},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7147693634033203},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6851073503494263},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6448504328727722},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5948742032051086},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5919640064239502},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5259373784065247},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5030209422111511},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4931604266166687},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.46070659160614014},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4547351002693176},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4518142342567444},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4348800778388977},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4330013394355774},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43051230907440186},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3783727288246155},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3446831703186035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.864493191242218},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.7729955315589905},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7147693634033203},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6851073503494263},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6448504328727722},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5948742032051086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5919640064239502},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5259373784065247},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5030209422111511},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4931604266166687},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.46070659160614014},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4547351002693176},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4518142342567444},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4348800778388977},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4330013394355774},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43051230907440186},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3783727288246155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3446831703186035},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg.2019.8756549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg.2019.8756549","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1924770834","https://openalex.org/W1962449414","https://openalex.org/W2064675550","https://openalex.org/W2066348332","https://openalex.org/W2138761194","https://openalex.org/W2146502635","https://openalex.org/W2154636774","https://openalex.org/W2171727224","https://openalex.org/W2287407690","https://openalex.org/W2547701628","https://openalex.org/W2594690981","https://openalex.org/W2726515241","https://openalex.org/W6607333740","https://openalex.org/W6640212811","https://openalex.org/W6681435938","https://openalex.org/W6685120548","https://openalex.org/W6734491695","https://openalex.org/W6740167877"],"related_works":["https://openalex.org/W1840351222","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,50,97,132],"propose":[4],"a":[5,36,53,99,125,134,144],"novel":[6,54],"visual":[7],"information":[8,34,115],"based":[9],"framework":[10],"to":[11,59,65,84,109,118],"solve":[12],"the":[13,25,46,67,73,77,82,104,113,120,129,159],"real-time":[14],"speech":[15,93,139],"activity":[16],"detection":[17],"problem.":[18],"Unlike":[19],"conventional":[20],"methods":[21],"which":[22,141],"commonly":[23],"use":[24,111],"audio":[26],"signal":[27],"as":[28,61],"input,":[29],"our":[30,162],"approach":[31,167],"incorporates":[32],"facial":[33],"into":[35],"deep":[37,68],"neural":[38,69,101],"network":[39,58,70,83,102],"for":[40,92],"feature":[41],"learning.":[42],"Instead":[43],"of":[44,76,112,128,143,147,154,161,170],"using":[45],"whole":[47],"input":[48,78],"image,":[49],"further":[51],"develop":[52],"end-to-end":[55],"landmark":[56],"pooling":[57],"act":[60],"an":[62],"attention-guide":[63],"scheme":[64,108],"help":[66],"only":[71],"focus":[72],"related":[74],"portion":[75],"image.":[79],"This":[80],"helps":[81],"precisely":[85],"and":[86,172],"efficiently":[87],"learn":[88],"highly":[89],"discriminative":[90],"features":[91],"activities.":[94],"What's":[95],"more,":[96],"implement":[98],"recurrent":[100,106],"with":[103],"gated":[105],"unit":[107],"make":[110],"sequential":[114],"from":[116,137],"video":[117,149],"produce":[119],"final":[121],"decision.":[122],"To":[123],"give":[124],"comprehensive":[126],"evaluation":[127],"proposed":[130,163],"method,":[131],"collect":[133],"large-scale":[135],"dataset":[136],"unconstrained":[138],"activities,":[140],"consists":[142],"large":[145],"number":[146],"speech/non-speech":[148],"sequences":[150],"under":[151],"various":[152],"kinds":[153],"degradation.":[155],"Experimental":[156],"results":[157],"demonstrate":[158],"superiority":[160],"pipeline":[164],"over":[165],"previous":[166],"in":[168],"terms":[169],"performance":[171],"efficiency.":[173]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}