{"id":"https://openalex.org/W2786625961","doi":"https://doi.org/10.1109/icassp.2018.8461370","title":"Multichannel Speech Separation with Recurrent Neural Networks from High-Order Ambisonics Recordings","display_name":"Multichannel Speech Separation with Recurrent Neural Networks from High-Order Ambisonics Recordings","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2786625961","doi":"https://doi.org/10.1109/icassp.2018.8461370","mag":"2786625961"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461370","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://hal.inria.fr/hal-01699759","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orange Labs, Cesson-S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Romain Serizel","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["Universite de Lorraine, Loria, Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite de Lorraine, Loria, Nancy, France","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I90183372"]}]},{"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/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Vincent","raw_affiliation_strings":["Universite de Lorraine, Loria, Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universite de Lorraine, Loria, Nancy, France","institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I90183372"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orange Labs, Cesson-S\u00e9vign\u00e9, France","institution_ids":["https://openalex.org/I19370010"]}]}],"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":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"40"},"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9983999729156494,"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/ambisonics","display_name":"Ambisonics","score":0.9636898040771484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7637584805488586},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6901291608810425},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5968010425567627},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5355707406997681},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5263489484786987},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5238547325134277},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.45634353160858154},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4477809965610504},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4381103515625},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.41969045996665955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34760332107543945},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3257605731487274},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2514764070510864},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.14440375566482544},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13722291588783264},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13027408719062805},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11114814877510071},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1079680323600769}],"concepts":[{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.9636898040771484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7637584805488586},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6901291608810425},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5968010425567627},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5355707406997681},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5263489484786987},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5238547325134277},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.45634353160858154},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4477809965610504},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4381103515625},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.41969045996665955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34760332107543945},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3257605731487274},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2514764070510864},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.14440375566482544},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13722291588783264},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13027408719062805},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11114814877510071},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1079680323600769},{"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/icassp.2018.8461370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461370","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-01699759v1","is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-01699759","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","raw_type":"\\ninfo:eu-repo/semantics/conferenceObject\\n"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01699759v1","is_oa":true,"landing_page_url":"https://hal.inria.fr/hal-01699759","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","raw_type":"\\ninfo:eu-repo/semantics/conferenceObject\\n"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W184563473","https://openalex.org/W1482149378","https://openalex.org/W1754457604","https://openalex.org/W1976805820","https://openalex.org/W1982172017","https://openalex.org/W2027926994","https://openalex.org/W2045346852","https://openalex.org/W2046869671","https://openalex.org/W2094461119","https://openalex.org/W2101609516","https://openalex.org/W2112469598","https://openalex.org/W2119494071","https://openalex.org/W2148024641","https://openalex.org/W2158143227","https://openalex.org/W2164502538","https://openalex.org/W2168729028","https://openalex.org/W2221409856","https://openalex.org/W2288645994","https://openalex.org/W2398042854","https://openalex.org/W2408744528","https://openalex.org/W2514741789","https://openalex.org/W2903382683","https://openalex.org/W2963488660","https://openalex.org/W6657506970","https://openalex.org/W6661981116","https://openalex.org/W6662385463","https://openalex.org/W6688843265"],"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/W4377371989","https://openalex.org/W4235050345","https://openalex.org/W2077498359","https://openalex.org/W4249456582"],"abstract_inverted_index":{"We":[0,11,30,82],"present":[1],"a":[2,13,18,22],"source":[3],"separation":[4],"system":[5],"for":[6],"high-order":[7],"ambisonics":[8],"(HOA)":[9],"contents.":[10],"derive":[12],"multichannel":[14],"spatial":[15],"filter":[16],"from":[17],"mask":[19],"estimated":[20],"by":[21,72,76],"long":[23],"short-term":[24],"memory":[25],"(LSTM)":[26],"recurrent":[27],"neural":[28],"network.":[29],"combine":[31],"one":[32],"channel":[33],"of":[34,40,55,57,66,90,102,115],"the":[35,38,47,53,58,64,88,91,95,103,107],"mixture":[36],"with":[37],"outputs":[39],"basic":[41],"HOA":[42],"beamformers":[43],"as":[44,86],"inputs":[45],"to":[46,100],"LSTM,":[48],"assuming":[49],"that":[50,84,101],"we":[51],"know":[52],"directions":[54],"arrival":[56],"directional":[59],"sources.":[60],"In":[61],"our":[62],"experiments,":[63],"speech":[65,97,109],"interest":[67],"can":[68],"be":[69],"corrupted":[70],"either":[71],"diffuse":[73],"noise":[74],"or":[75],"an":[77],"equally":[78],"loud":[79],"competing":[80,96],"speaker.":[81],"show":[83],"adding":[85],"input":[87],"output":[89],"beamformer":[92,104],"steered":[93,105],"toward":[94,106],"in":[98,113],"addition":[99],"target":[108],"brings":[110],"significant":[111],"improvements":[112],"terms":[114],"word":[116],"error":[117],"rate.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}