{"id":"https://openalex.org/W2795437830","doi":"https://doi.org/10.1109/icassp.2018.8462100","title":"Accounting for Room Acoustics in Audio-Visual Multi-Speaker Tracking","display_name":"Accounting for Room Acoustics in Audio-Visual Multi-Speaker Tracking","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2795437830","doi":"https://doi.org/10.1109/icassp.2018.8462100","mag":"2795437830"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-01718114","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011762462","display_name":"Yutong Ban","orcid":"https://orcid.org/0000-0001-5396-9251"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yutong Ban","raw_affiliation_strings":["INRIA Grenoble Rhone-Alpes, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358313","display_name":"Xiaofei Li","orcid":"https://orcid.org/0000-0003-0393-9905"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xiaofei Li","raw_affiliation_strings":["INRIA Grenoble Rhone-Alpes, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["INRIA Grenoble Rhone-Alpes, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020392160","display_name":"Laurent Girin","orcid":"https://orcid.org/0000-0002-9214-8760"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Girin","raw_affiliation_strings":["INRIA Grenoble Rhone-Alpes, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"raw_affiliation_string":"GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078307335","display_name":"Radu Horaud","orcid":"https://orcid.org/0000-0001-5232-024X"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Radu Horaud","raw_affiliation_strings":["INRIA Grenoble Rhone-Alpes, France","PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA Grenoble Rhone-Alpes, France","institution_ids":["https://openalex.org/I1326498283"]},{"raw_affiliation_string":"PERCEPTION  - Interpretation and Modelling of Images and Videos (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot, France - France)","institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6553","last_page":"6557"},"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":0.9973999857902527,"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"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9952999949455261,"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":0.7659754753112793},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.7177873849868774},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5577605962753296},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4393874406814575},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.43114301562309265},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4218616187572479},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41260087490081787},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3514277935028076},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35097819566726685},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.228364497423172},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11248049139976501}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7659754753112793},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.7177873849868774},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5577605962753296},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4393874406814575},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.43114301562309265},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4218616187572479},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41260087490081787},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3514277935028076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35097819566726685},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.228364497423172},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11248049139976501},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2018.8462100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01718114v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01718114","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2018 - IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Alberta, Canada. pp.6553-6557, ⟨10.1109/ICASSP.2018.8462100⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01718114v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01718114","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2018 - IEEE International Conference on Acoustics, Speech and Signal Processing, Apr 2018, Calgary, Alberta, Canada. pp.6553-6557, ⟨10.1109/ICASSP.2018.8462100⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1552633171","https://openalex.org/W1873027057","https://openalex.org/W1947177743","https://openalex.org/W2016157229","https://openalex.org/W2088725063","https://openalex.org/W2131968171","https://openalex.org/W2138414774","https://openalex.org/W2156676906","https://openalex.org/W2159801939","https://openalex.org/W2167868656","https://openalex.org/W2231821870","https://openalex.org/W2283599234","https://openalex.org/W2291627510","https://openalex.org/W2316138215","https://openalex.org/W2510977782","https://openalex.org/W2517955251","https://openalex.org/W2552290276","https://openalex.org/W2568308529","https://openalex.org/W2588791810","https://openalex.org/W2675830001","https://openalex.org/W2697319950","https://openalex.org/W2752604219","https://openalex.org/W3100336094","https://openalex.org/W3100987222","https://openalex.org/W6633052144","https://openalex.org/W6699662792","https://openalex.org/W6725898459","https://openalex.org/W6740061210","https://openalex.org/W6743757214"],"related_works":["https://openalex.org/W1656519308","https://openalex.org/W2042717753","https://openalex.org/W2037265366","https://openalex.org/W2022849831","https://openalex.org/W2391832549","https://openalex.org/W2286653370","https://openalex.org/W1499578372","https://openalex.org/W2368849850","https://openalex.org/W1799937301","https://openalex.org/W2026603686"],"abstract_inverted_index":{"Multiple-speaker":[0],"tracking":[1],"is":[2,66],"a":[3],"crucial":[4],"task":[5],"for":[6],"many":[7],"applications.":[8],"In":[9],"real-world":[10],"scenarios,":[11],"exploiting":[12],"the":[13,25,60,63,72],"complementarity":[14],"between":[15],"auditory":[16],"and":[17],"visual":[18,26],"data":[19],"enables":[20],"to":[21,36,46],"track":[22],"people":[23],"outside":[24],"field":[27],"of":[28,62],"view.":[29],"However,":[30],"practical":[31],"methods":[32],"must":[33],"be":[34],"robust":[35],"changes":[37,70],"in":[38,71],"acoustic":[39,73],"conditions,":[40],"e.g.":[41],"reverberation.":[42],"We":[43],"investigate":[44],"how":[45],"combine":[47],"state-of-the-art":[48],"audio-source":[49],"localization":[50],"techniques":[51],"with":[52],"Bayesian":[53],"multi-person":[54],"tracking.":[55],"Our":[56],"experiments":[57],"demonstrate":[58],"that":[59],"performance":[61],"proposed":[64],"system":[65],"not":[67],"affected":[68],"by":[69],"environment.":[74]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}