{"id":"https://openalex.org/W2917254586","doi":"https://doi.org/10.1109/jstsp.2019.2900164","title":"CRNN-Based Multiple DoA Estimation Using Acoustic Intensity Features for Ambisonics Recordings","display_name":"CRNN-Based Multiple DoA Estimation Using Acoustic Intensity Features for Ambisonics Recordings","publication_year":2019,"publication_date":"2019-02-18","ids":{"openalex":"https://openalex.org/W2917254586","doi":"https://doi.org/10.1109/jstsp.2019.2900164","mag":"2917254586"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2019.2900164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2900164","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-01839883","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003971949","display_name":"Laur\u00e9line Perotin","orcid":"https://orcid.org/0000-0002-4373-6750"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laureline Perotin","raw_affiliation_strings":["Orange Labs, Cesson S\u00e9vign\u00e9, France","Orange Labs [Cesson-S\u00e9vign\u00e9] (4 Rue du Clos Courtel, 35510 Cesson-S\u00e9vign\u00e9 - France)","MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"raw_orcid":"https://orcid.org/0000-0002-4373-6750","affiliations":[{"raw_affiliation_string":"Orange Labs, Cesson S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"Orange Labs [Cesson-S\u00e9vign\u00e9] (4 Rue du Clos Courtel, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Romain Serizel","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["Orange Labs, Cesson S\u00e9vign\u00e9, France","MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orange Labs, Cesson S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065635001","display_name":"Emmanuel Vincent","orcid":"https://orcid.org/0000-0002-0183-7289"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Vincent","raw_affiliation_strings":["Orange Labs, Cesson S\u00e9vign\u00e9, France","MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)"],"raw_orcid":"https://orcid.org/0000-0002-0183-7289","affiliations":[{"raw_affiliation_string":"Orange Labs, Cesson S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication (France)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040735296","display_name":"Alexandre Gu\u00e9rin","orcid":"https://orcid.org/0000-0003-2437-5977"},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexandre Guerin","raw_affiliation_strings":["Orange Labs, Cesson S\u00e9vign\u00e9, France","Orange Labs [Cesson-S\u00e9vign\u00e9] (4 Rue du Clos Courtel, 35510 Cesson-S\u00e9vign\u00e9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orange Labs, Cesson S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"Orange Labs [Cesson-S\u00e9vign\u00e9] (4 Rue du Clos Courtel, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":["https://openalex.org/I19370010"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I19370010"],"apc_list":null,"apc_paid":null,"fwci":13.1752,"has_fulltext":false,"cited_by_count":137,"citation_normalized_percentile":{"value":0.99206853,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"13","issue":"1","first_page":"22","last_page":"33"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/ambisonics","display_name":"Ambisonics","score":0.975583553314209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.827120304107666},{"id":"https://openalex.org/keywords/direction-of-arrival","display_name":"Direction of arrival","score":0.5510162711143494},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.547728419303894},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5131834149360657},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5121660232543945},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4354487657546997},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.41308704018592834},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41147133708000183},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3772379457950592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3406762480735779},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.26986929774284363},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.25623631477355957},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1053447425365448},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08379679918289185}],"concepts":[{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.975583553314209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827120304107666},{"id":"https://openalex.org/C172051844","wikidata":"https://www.wikidata.org/wiki/Q5280438","display_name":"Direction of arrival","level":3,"score":0.5510162711143494},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.547728419303894},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5131834149360657},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5121660232543945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4354487657546997},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.41308704018592834},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41147133708000183},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3772379457950592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3406762480735779},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.26986929774284363},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.25623631477355957},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1053447425365448},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08379679918289185},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jstsp.2019.2900164","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2019.2900164","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-01839883v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01839883","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":"IEEE Journal of Selected Topics in Signal Processing, 2019, Special Issue on Acoustic Source Localization and Tracking in Dynamic Real-life Scenes, 13 (1), pp.22-33. ⟨10.1109/jstsp.2019.2900164⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01839883v2","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01839883","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":"IEEE Journal of Selected Topics in Signal Processing, 2019, Special Issue on Acoustic Source Localization and Tracking in Dynamic Real-life Scenes, 13 (1), pp.22-33. ⟨10.1109/jstsp.2019.2900164⟩","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W184563473","https://openalex.org/W1504118426","https://openalex.org/W1511723925","https://openalex.org/W1515296674","https://openalex.org/W1555217905","https://openalex.org/W1582886869","https://openalex.org/W1603075283","https://openalex.org/W1787224781","https://openalex.org/W1836465849","https://openalex.org/W1876052200","https://openalex.org/W1966081805","https://openalex.org/W1982687260","https://openalex.org/W1984043525","https://openalex.org/W2025127228","https://openalex.org/W2037814094","https://openalex.org/W2046317813","https://openalex.org/W2089473323","https://openalex.org/W2096429319","https://openalex.org/W2096439661","https://openalex.org/W2100818340","https://openalex.org/W2104617572","https://openalex.org/W2113638573","https://openalex.org/W2114863372","https://openalex.org/W2117029426","https://openalex.org/W2117678320","https://openalex.org/W2128131274","https://openalex.org/W2149648624","https://openalex.org/W2222512263","https://openalex.org/W2403149086","https://openalex.org/W2405404760","https://openalex.org/W2490695385","https://openalex.org/W2598194391","https://openalex.org/W2611469656","https://openalex.org/W2611943505","https://openalex.org/W2657631929","https://openalex.org/W2745195618","https://openalex.org/W2761044439","https://openalex.org/W2771922328","https://openalex.org/W2786625961","https://openalex.org/W2793357660","https://openalex.org/W2801757532","https://openalex.org/W2883288608","https://openalex.org/W2887883376","https://openalex.org/W2888793942","https://openalex.org/W2888842465","https://openalex.org/W2897088495","https://openalex.org/W2903382683","https://openalex.org/W2918296821","https://openalex.org/W2964045325","https://openalex.org/W2964231383","https://openalex.org/W2964342924","https://openalex.org/W3104757150","https://openalex.org/W4206633762","https://openalex.org/W4249052411","https://openalex.org/W6630773358","https://openalex.org/W6630851631","https://openalex.org/W6638667902","https://openalex.org/W6659849957","https://openalex.org/W6674621238","https://openalex.org/W6682325752","https://openalex.org/W6713369370","https://openalex.org/W6746576432","https://openalex.org/W6757107679"],"related_works":["https://openalex.org/W62656364","https://openalex.org/W4387871131","https://openalex.org/W2403497458","https://openalex.org/W2305368260","https://openalex.org/W3108333885","https://openalex.org/W1978521983","https://openalex.org/W3216979959","https://openalex.org/W4251115075","https://openalex.org/W2305616225","https://openalex.org/W2982680886"],"abstract_inverted_index":{"Localizing":[0],"audio":[1],"sources":[2,12,39],"is":[3],"challenging":[4],"in":[5,29,103,118],"real":[6,125],"reverberant":[7],"environments,":[8,120],"especially":[9],"when":[10],"several":[11],"are":[13,101],"active.":[14],"We":[15,61,74,107],"propose":[16,62],"to":[17,31,63,111,124,145],"use":[18,64],"a":[19,41,52,56,85,104],"neural":[20,80],"network":[21,81],"built":[22],"from":[23,40,67,121],"stacked":[24],"convolutional":[25],"and":[26],"recurrent":[27],"layers":[28],"order":[30],"estimate":[32],"the":[33,47,68,76,79,98,113,137],"directions":[34,48],"of":[35,37,49,55,59,78,84,97,115],"arrival":[36,50],"multiple":[38],"first-order":[42],"Ambisonics":[43,147],"recording.":[44],"It":[45],"returns":[46],"over":[51],"discrete":[53],"grid":[54],"known":[57],"number":[58],"sources.":[60,132],"features":[65,139],"derived":[66],"acoustic":[69],"intensity":[70],"vector":[71],"as":[72],"inputs.":[73,148],"analyze":[75],"behavior":[77],"by":[82],"means":[83],"visualization":[86],"technique":[87],"called":[88],"layerwise":[89],"relevance":[90],"propagation.":[91],"This":[92],"analysis":[93],"highlights":[94],"which":[95],"parts":[96],"input":[99],"signal":[100],"relevant":[102],"given":[105],"situation.":[106],"also":[108],"conduct":[109],"experiments":[110],"evaluate":[112],"performance":[114],"our":[116],"system":[117],"various":[119],"simulated":[122],"rooms":[123],"recordings,":[126],"with":[127,143],"one":[128],"or":[129],"two":[130],"speech":[131],"The":[133],"results":[134],"show":[135],"that":[136],"proposed":[138],"significantly":[140],"improve":[141],"performances":[142],"respect":[144],"raw":[146]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":8}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}