{"id":"https://openalex.org/W2586878855","doi":"https://doi.org/10.1109/slt.2016.7846321","title":"Audio-visual speech activity detection in a two-speaker scenario incorporating depth information from a profile or frontal view","display_name":"Audio-visual speech activity detection in a two-speaker scenario incorporating depth information from a profile or frontal view","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2586878855","doi":"https://doi.org/10.1109/slt.2016.7846321","mag":"2586878855"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2016.7846321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5015117681","display_name":"Spyridon Thermos","orcid":"https://orcid.org/0000-0001-5458-6906"},"institutions":[{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]},{"id":"https://openalex.org/I4210134249","display_name":"Centre for Research and Technology Hellas","ror":"https://ror.org/03bndpq63","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210134249"]},{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Spyridon Thermos","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Thessaly, Volos, Greece","Information Technologies Institute, CERTH, Thermi, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]},{"raw_affiliation_string":"Information Technologies Institute, CERTH, Thermi, Thessaloniki, Greece","institution_ids":["https://openalex.org/I4210093649","https://openalex.org/I4210134249"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124"},"institutions":[{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]},{"id":"https://openalex.org/I145722265","display_name":"University of Thessaly","ror":"https://ror.org/04v4g9h31","country_code":"GR","type":"education","lineage":["https://openalex.org/I145722265"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":["Athena Research and Innovation Center, Maroussi, Athens, Greece","Department of Electrical and Computer Engineering, University of Thessaly, Volos, Greece"],"affiliations":[{"raw_affiliation_string":"Athena Research and Innovation Center, Maroussi, Athens, Greece","institution_ids":["https://openalex.org/I4210156054"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Thessaly, Volos, Greece","institution_ids":["https://openalex.org/I145722265"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015117681"],"corresponding_institution_ids":["https://openalex.org/I145722265","https://openalex.org/I4210093649","https://openalex.org/I4210134249"],"apc_list":null,"apc_paid":null,"fwci":1.5303,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84962715,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"lncs 8655","issue":null,"first_page":"579","last_page":"584"},"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":0.9976999759674072,"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":0.9962000250816345,"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":0.8258585929870605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6901105642318726},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5654498934745789},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5012025833129883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48868992924690247},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.44327491521835327},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.43730059266090393},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3758149743080139},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35876893997192383},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3080739676952362}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8258585929870605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6901105642318726},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5654498934745789},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5012025833129883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48868992924690247},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.44327491521835327},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.43730059266090393},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3758149743080139},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35876893997192383},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3080739676952362}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2016.7846321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2016.7846321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:ir.lib.uth.gr:11615/79699","is_oa":false,"landing_page_url":"http://hdl.handle.net/11615/79699","pdf_url":null,"source":{"id":"https://openalex.org/S4306400243","display_name":"University of Thessaly Institutional Repository (University of Thessaly)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145722265","host_organization_name":"University of Thessaly","host_organization_lineage":["https://openalex.org/I145722265"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2016 IEEE Workshop on Spoken Language Technology, SLT 2016 - Proceedings","raw_type":"conferenceItem"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W25302482","https://openalex.org/W1013543043","https://openalex.org/W1489488446","https://openalex.org/W1503933356","https://openalex.org/W1537011605","https://openalex.org/W1595802121","https://openalex.org/W1608493013","https://openalex.org/W1736374775","https://openalex.org/W1970955362","https://openalex.org/W1971901154","https://openalex.org/W1972102638","https://openalex.org/W1974783905","https://openalex.org/W1993583497","https://openalex.org/W2016157229","https://openalex.org/W2019256855","https://openalex.org/W2024490110","https://openalex.org/W2038010270","https://openalex.org/W2042608483","https://openalex.org/W2049893888","https://openalex.org/W2063880242","https://openalex.org/W2075973450","https://openalex.org/W2081074144","https://openalex.org/W2090088747","https://openalex.org/W2099570340","https://openalex.org/W2102863932","https://openalex.org/W2125336414","https://openalex.org/W2126693545","https://openalex.org/W2133115605","https://openalex.org/W2136155248","https://openalex.org/W2148659689","https://openalex.org/W2153635508","https://openalex.org/W2168744723","https://openalex.org/W2181253919","https://openalex.org/W2184549941","https://openalex.org/W2403676906","https://openalex.org/W2556171197","https://openalex.org/W2556428200","https://openalex.org/W2572911620","https://openalex.org/W2898799761","https://openalex.org/W3144828656","https://openalex.org/W3157685993","https://openalex.org/W6601090573","https://openalex.org/W6632221376","https://openalex.org/W6635954256","https://openalex.org/W6636419984","https://openalex.org/W6637571906","https://openalex.org/W6678809451","https://openalex.org/W6681898093","https://openalex.org/W6713394859","https://openalex.org/W6729699919","https://openalex.org/W6729915111","https://openalex.org/W6732472226"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W2122924390","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2550171623","https://openalex.org/W2009814707"],"abstract_inverted_index":{"Motivated":[0],"by":[1,120],"increasing":[2],"popularity":[3],"of":[4,17,51,127],"depth":[5,18,42,128,134],"visual":[6],"sensors,":[7],"such":[8],"as":[9],"the":[10,15,52,59,80,98,125,132],"Kinect":[11],"device,":[12],"we":[13],"investigate":[14],"utility":[16],"information":[19],"in":[20,131],"audio-visual":[21,117],"speech":[22,34,89,138],"activity":[23,90,139],"detection.":[24],"A":[25],"two-subject":[26],"scenario":[27],"is":[28,55,69],"assumed,":[29],"allowing":[30],"to":[31,107],"also":[32],"consider":[33],"overlap.":[35],"Two":[36],"sensory":[37],"setups":[38],"are":[39,104,112],"employed,":[40],"where":[41],"video":[43,62,75],"captures":[44],"either":[45],"a":[46,77,115],"frontal":[47,133],"or":[48],"profile":[49],"view":[50,82,135],"subjects,":[53],"and":[54,63,73,141],"subsequently":[56],"combined":[57,106],"with":[58],"corresponding":[60],"planar":[61,74],"audio":[64,72],"streams.":[65,101],"Further,":[66],"multi-view":[67],"fusion":[68],"regarded,":[70],"using":[71],"from":[76],"sensor":[78],"at":[79],"complementary":[81],"setup.":[83],"Support":[84],"vector":[85],"machines":[86],"provide":[87],"temporal":[88],"classification":[91],"for":[92],"each":[93],"visually":[94],"detected":[95],"subject,":[96],"fusing":[97],"available":[99],"modality":[100],"Classification":[102],"results":[103],"further":[105],"yield":[108],"speaker":[109,142],"diarization.":[110],"Experiments":[111],"reported":[113],"on":[114],"suitable":[116],"corpus":[118],"recorded":[119],"two":[121],"Kinects.":[122],"Results":[123],"demonstrate":[124],"benefits":[126],"information,":[129],"particularly":[130],"setup,":[136],"reducing":[137],"detection":[140],"diarization":[143],"errors":[144],"over":[145],"systems":[146],"that":[147],"ignore":[148],"it.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}