{"id":"https://openalex.org/W3160878746","doi":"https://doi.org/10.1109/icassp39728.2021.9414415","title":"Synthetic Data For Dnn-Based Doa Estimation of Indoor Speech","display_name":"Synthetic Data For Dnn-Based Doa Estimation of Indoor Speech","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160878746","doi":"https://doi.org/10.1109/icassp39728.2021.9414415","mag":"3160878746"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11250/2824872","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023774362","display_name":"Femke B. Gelderblom","orcid":"https://orcid.org/0000-0002-1034-4427"},"institutions":[{"id":"https://openalex.org/I173888879","display_name":"SINTEF","ror":"https://ror.org/01f677e56","country_code":"NO","type":"facility","lineage":["https://openalex.org/I173888879"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Femke B. Gelderblom","raw_affiliation_strings":["NTNU &#x0026; SINTEF,Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTNU &#x0026; SINTEF,Norway","institution_ids":["https://openalex.org/I173888879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701079","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-3086-7273"},"institutions":[{"id":"https://openalex.org/I173888879","display_name":"SINTEF","ror":"https://ror.org/01f677e56","country_code":"NO","type":"facility","lineage":["https://openalex.org/I173888879"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["SINTEF,Norway","SINTEF, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SINTEF,Norway","institution_ids":["https://openalex.org/I173888879"]},{"raw_affiliation_string":"SINTEF, Norway","institution_ids":["https://openalex.org/I173888879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054817641","display_name":"Johannes Kvam","orcid":"https://orcid.org/0000-0003-1677-8143"},"institutions":[{"id":"https://openalex.org/I173888879","display_name":"SINTEF","ror":"https://ror.org/01f677e56","country_code":"NO","type":"facility","lineage":["https://openalex.org/I173888879"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Johannes Kvam","raw_affiliation_strings":["SINTEF,Norway","SINTEF, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SINTEF,Norway","institution_ids":["https://openalex.org/I173888879"]},{"raw_affiliation_string":"SINTEF, Norway","institution_ids":["https://openalex.org/I173888879"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064171039","display_name":"Tor Andr\u00e9 Myrvoll","orcid":"https://orcid.org/0000-0001-6286-9148"},"institutions":[{"id":"https://openalex.org/I173888879","display_name":"SINTEF","ror":"https://ror.org/01f677e56","country_code":"NO","type":"facility","lineage":["https://openalex.org/I173888879"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Tor Andre Myrvoll","raw_affiliation_strings":["NTNU &#x0026; SINTEF,Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTNU &#x0026; SINTEF,Norway","institution_ids":["https://openalex.org/I173888879"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0074,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.87092455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4390","last_page":"4394"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7485449314117432},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5862732529640198},{"id":"https://openalex.org/keywords/azimuth","display_name":"Azimuth","score":0.5029804110527039},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4865368902683258},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4854162633419037},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4815157353878021},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.45921751856803894},{"id":"https://openalex.org/keywords/directivity","display_name":"Directivity","score":0.44695812463760376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.429492712020874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14024999737739563},{"id":"https://openalex.org/keywords/antenna","display_name":"Antenna (radio)","score":0.13010773062705994},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11186110973358154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7485449314117432},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5862732529640198},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.5029804110527039},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4865368902683258},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4854162633419037},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4815157353878021},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.45921751856803894},{"id":"https://openalex.org/C189039984","wikidata":"https://www.wikidata.org/wiki/Q8225412","display_name":"Directivity","level":3,"score":0.44695812463760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.429492712020874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14024999737739563},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.13010773062705994},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11186110973358154},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414415","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414415","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ntnuopen.ntnu.no:11250/2824872","is_oa":true,"landing_page_url":"https://hdl.handle.net/11250/2824872","pdf_url":null,"source":{"id":"https://openalex.org/S4306401716","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"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":"4390-4394","raw_type":"info:eu-repo/semantics/bookPart"},{"id":"pmh:oai:sintef.brage.unit.no:11250/3048554","is_oa":true,"landing_page_url":"https://hdl.handle.net/11250/3048554","pdf_url":null,"source":{"id":"https://openalex.org/S4306401716","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"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":"4390-4394","raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":{"id":"pmh:oai:ntnuopen.ntnu.no:11250/2824872","is_oa":true,"landing_page_url":"https://hdl.handle.net/11250/2824872","pdf_url":null,"source":{"id":"https://openalex.org/S4306401716","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"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":"4390-4394","raw_type":"info:eu-repo/semantics/bookPart"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1603075283","https://openalex.org/W1984823839","https://openalex.org/W2048489440","https://openalex.org/W2106411961","https://openalex.org/W2113638573","https://openalex.org/W2113744809","https://openalex.org/W2117678320","https://openalex.org/W2135817141","https://openalex.org/W2337621096","https://openalex.org/W2403149086","https://openalex.org/W2611943505","https://openalex.org/W2617258110","https://openalex.org/W2883288608","https://openalex.org/W2885091335","https://openalex.org/W2896274130","https://openalex.org/W2917254586","https://openalex.org/W2940285530","https://openalex.org/W2960533729","https://openalex.org/W3104757150","https://openalex.org/W6636126089","https://openalex.org/W6676179485","https://openalex.org/W6703471520","https://openalex.org/W6712697115","https://openalex.org/W6765820759"],"related_works":["https://openalex.org/W2076543106","https://openalex.org/W2019891950","https://openalex.org/W2085842814","https://openalex.org/W2523437662","https://openalex.org/W4387048144","https://openalex.org/W2492135063","https://openalex.org/W2362514456","https://openalex.org/W2766585573","https://openalex.org/W4387490624","https://openalex.org/W4286643620"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,38,85,106,131,141,147],"use":[4],"of":[5,22,26,32,87,143],"different":[6],"room":[7],"impulse":[8],"response":[9,108],"(RIR)":[10],"simulation":[11],"methods":[12,46],"for":[13,17,70],"synthesizing":[14],"training":[15,88],"data":[16],"deep":[18,56],"neural":[19,57],"network-based":[20],"direction":[21],"arrival":[23],"(DOA)":[24],"estimation":[25],"speech":[27],"in":[28],"reverberant":[29],"rooms.Different":[30],"sets":[31],"synthetic":[33],"RIRs":[34,90,124],"are":[35,61,75],"obtained":[36,79],"using":[37],"image":[39],"source":[40,51],"method":[41],"(ISM)":[42],"and":[43],"more":[44],"advanced":[45],"including":[47],"diffuse":[48],"reflections":[49],"and/or":[50],"directivity.":[52],"Multi-layer":[53],"perceptron":[54],"(MLP)":[55],"network":[58],"(DNN)":[59],"models":[60,74,97,121],"trained":[62,122],"on":[63,77],"generalized":[64],"cross":[65],"correlation":[66],"(GCC)":[67],"features":[68,78],"extracted":[69],"each":[71],"set.":[72],"Finally,":[73],"tested":[76],"from":[80,91,125],"measured":[81],"RIRs.This":[82],"study":[83],"shows":[84],"importance":[86],"with":[89,110,116,123],"directive":[92],"sources,":[93],"as":[94],"resultant":[95],"DOA":[96],"achieved":[98],"up":[99],"to":[100,105],"51%":[101],"error":[102],"reduction":[103],"compared":[104],"steered":[107],"power":[109],"phase":[111],"transform":[112],"(SRP-PHAT)":[113],"baseline":[114],"(significant":[115],"p":[117],"<<":[118],".01),":[119],"while":[120],"omnidirectional":[126],"sources":[127],"did":[128],"worse":[129],"than":[130],"baseline.":[132],"The":[133],"performance":[134],"difference":[135],"was":[136],"specifically":[137],"present":[138],"when":[139],"estimating":[140],"azimuth":[142],"speakers":[144],"not":[145],"facing":[146],"array":[148],"directly.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}