{"id":"https://openalex.org/W3016158375","doi":"https://doi.org/10.1109/icassp40776.2020.9054005","title":"A Dynamic Stream Weight Backprop Kalman Filter for Audiovisual Speaker Tracking","display_name":"A Dynamic Stream Weight Backprop Kalman Filter for Audiovisual Speaker Tracking","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016158375","doi":"https://doi.org/10.1109/icassp40776.2020.9054005","mag":"3016158375"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5035233948","display_name":"Christopher Schymura","orcid":"https://orcid.org/0000-0002-6128-3556"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christopher Schymura","raw_affiliation_strings":["Institute of Communication Acoustics, Ruhr University Bochum, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr University Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070624983","display_name":"Tsubasa Ochiai","orcid":"https://orcid.org/0000-0002-2519-2032"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsubasa Ochiai","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069398831","display_name":"Keisuke Kinoshita","orcid":"https://orcid.org/0009-0008-7987-8188"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Kinoshita","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007017640","display_name":"Dorothea Kolossa","orcid":"https://orcid.org/0000-0003-0678-3053"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dorothea Kolossa","raw_affiliation_strings":["Institute of Communication Acoustics, Ruhr University Bochum, Bochum, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr University Bochum, Bochum, Germany","institution_ids":["https://openalex.org/I904495901"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":null,"first_page":"581","last_page":"585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.7949776649475098},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7893413305282593},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5553068518638611},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.5394232273101807},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5191349387168884},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48934000730514526},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4805360436439514},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4727890193462372},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4693784713745117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4679141640663147},{"id":"https://openalex.org/keywords/extended-kalman-filter","display_name":"Extended Kalman filter","score":0.4162563681602478},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3217059373855591},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2406425178050995},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0999460220336914},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08752316236495972}],"concepts":[{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.7949776649475098},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7893413305282593},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5553068518638611},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.5394232273101807},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5191349387168884},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48934000730514526},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4805360436439514},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4727890193462372},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4693784713745117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4679141640663147},{"id":"https://openalex.org/C206833254","wikidata":"https://www.wikidata.org/wiki/Q5421817","display_name":"Extended Kalman filter","level":3,"score":0.4162563681602478},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3217059373855591},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2406425178050995},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0999460220336914},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08752316236495972},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W834081922","https://openalex.org/W1518556865","https://openalex.org/W1522301498","https://openalex.org/W1595802121","https://openalex.org/W1971791733","https://openalex.org/W2008750120","https://openalex.org/W2064675550","https://openalex.org/W2086384421","https://openalex.org/W2087681821","https://openalex.org/W2121551559","https://openalex.org/W2129866629","https://openalex.org/W2133564696","https://openalex.org/W2138414774","https://openalex.org/W2155323221","https://openalex.org/W2171362583","https://openalex.org/W2316138215","https://openalex.org/W2395463083","https://openalex.org/W2402812906","https://openalex.org/W2527729766","https://openalex.org/W2576672819","https://openalex.org/W2586219009","https://openalex.org/W2751471435","https://openalex.org/W2763188033","https://openalex.org/W2774812352","https://openalex.org/W2899759163","https://openalex.org/W2912752824","https://openalex.org/W2963166838","https://openalex.org/W2963430173","https://openalex.org/W2963654155","https://openalex.org/W2963714390","https://openalex.org/W2964199361","https://openalex.org/W2964308564","https://openalex.org/W2964342924","https://openalex.org/W3011514609","https://openalex.org/W4288350815","https://openalex.org/W6623316541","https://openalex.org/W6678395162","https://openalex.org/W6679434410","https://openalex.org/W6712730493","https://openalex.org/W6713608217","https://openalex.org/W6744063608","https://openalex.org/W6758371532","https://openalex.org/W6760124821"],"related_works":["https://openalex.org/W4239286941","https://openalex.org/W2088845016","https://openalex.org/W589102260","https://openalex.org/W1966421350","https://openalex.org/W1868434454","https://openalex.org/W2089114113","https://openalex.org/W4366984740","https://openalex.org/W1918707195","https://openalex.org/W2162299404","https://openalex.org/W2103062922"],"abstract_inverted_index":{"Audiovisual":[0],"speaker":[1,119],"tracking":[2,120],"is":[3],"an":[4],"application":[5],"that":[6,122],"has":[7],"been":[8],"tackled":[9],"by":[10,56],"a":[11,28,74,111,140],"wide":[12],"range":[13],"of":[14,48,62,78,101,138,143],"classical":[15],"approaches":[16],"based":[17],"on":[18,117],"Gaussian":[19],"filters,":[20],"most":[21],"notably":[22],"the":[23,46,60,79,99,102,105,123,135],"well-known":[24],"Kalman":[25,30,80],"filter.":[26],"Recently,":[27],"specific":[29],"filter":[31,81],"implementation":[32,77],"was":[33],"proposed":[34,124],"for":[35,96],"this":[36,71],"task,":[37],"which":[38],"incorporated":[39],"dynamic":[40,83,106],"stream":[41,84,107],"weights":[42],"to":[43,129],"explicitly":[44],"control":[45],"influence":[47],"acoustic":[49],"and":[50,104,145],"visual":[51],"observations":[52],"during":[53],"estimation.":[54],"Inspired":[55],"recent":[57],"progress":[58],"in":[59,110],"context":[61],"integrating":[63],"uncertainty":[64,148],"estimates":[65],"into":[66],"modern":[67],"deep":[68,75],"learning":[69],"frameworks,":[70],"paper":[72],"proposes":[73],"neural-network-based":[76],"with":[82,134],"weights,":[85],"whose":[86],"parameters":[87,100,144],"can":[88],"be":[89],"learned":[90],"via":[91],"standard":[92],"backpropagation.":[93],"This":[94],"allows":[95],"jointly":[97],"optimizing":[98],"model":[103,125],"weight":[108],"estimator":[109],"unified":[112],"framework.":[113],"An":[114],"experimental":[115],"study":[116],"audiovisual":[118],"shows":[121,126],"comparable":[127],"performance":[128],"state-of-the-art":[130],"recurrent":[131],"neural":[132],"networks":[133],"additional":[136],"advantage":[137],"requiring":[139],"smaller":[141],"number":[142],"providing":[146],"explicit":[147],"information.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}