{"id":"https://openalex.org/W3197645165","doi":"https://doi.org/10.21437/interspeech.2021-886","title":"CNN-Based Processing of Acoustic and Radio Frequency Signals for Speaker Localization from MAVs","display_name":"CNN-Based Processing of Acoustic and Radio Frequency Signals for Speaker Localization from MAVs","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3197645165","doi":"https://doi.org/10.21437/interspeech.2021-886","mag":"3197645165"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-886","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","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/A5066959657","display_name":"Andrea Toma","orcid":"https://orcid.org/0000-0002-2826-0803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrea Toma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008270926","display_name":"Daniele Salvati","orcid":"https://orcid.org/0000-0002-8042-0333"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniele Salvati","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019634521","display_name":"Carlo Drioli","orcid":"https://orcid.org/0000-0001-6091-4953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carlo Drioli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078277002","display_name":"Gian Luca Foresti","orcid":"https://orcid.org/0000-0002-8425-6892"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gian Luca Foresti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2147","last_page":"2151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9663000106811523,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9663000106811523,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9661999940872192,"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/computer-science","display_name":"Computer science","score":0.7118882536888123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5525375604629517},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.44977471232414246},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.17801976203918457},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.07602295279502869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7118882536888123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5525375604629517},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.44977471232414246},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.17801976203918457},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.07602295279502869}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-886","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:air.uniud.it:11390/1218670","is_oa":false,"landing_page_url":"http://hdl.handle.net/11390/1218670","pdf_url":null,"source":{"id":"https://openalex.org/S4306401163","display_name":"Institutional Research Information System (University of Udine)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I129043915","host_organization_name":"University of Udine","host_organization_lineage":["https://openalex.org/I129043915"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"A":[0,63],"novel":[1],"speaker":[2],"localization":[3,86],"algorithm":[4],"from":[5,87,111],"micro":[6],"aerial":[7,48],"vehicles":[8,49],"(MAVs)":[9],"is":[10,73],"investigated.":[11],"It":[12],"introduces":[13],"a":[14,70],"joint":[15],"direction":[16],"of":[17,29,39,82,106,124],"arrival":[18],"(DOA)":[19],"and":[20,27,52,56,58,97,100,109,122,131,135],"distance":[21,110],"prediction":[22],"method":[23],"based":[24],"on":[25],"processing":[26],"fusion":[28,71,116],"the":[30,40,80,84,95,101,107,112,115,120,128,142],"multi-channel":[31,88],"speech":[32,89,96],"data":[33],"with":[34,69,79,141],"radio":[35],"frequency":[36],"(RF)":[37],"measurements":[38],"received":[41],"signal":[42],"strength.":[43],"Possible":[44],"applications":[45],"include":[46],"unmanned":[47],"(UAVs)based":[50],"reconnaissance":[51],"surveillance":[53],"against":[54],"intrusions":[55],"search":[57],"rescue":[59],"in":[60],"hostile":[61],"environments.":[62],"3-stages":[64],"convolutional":[65],"neural":[66],"network":[67,103],"(CNN)":[68],"layer":[72],"proposed":[74],"to":[75],"perform":[76],"this":[77,125],"task":[78],"objective":[81],"augmenting":[83],"source":[85,113],"signals.":[90],"Two":[91],"parallel":[92],"CNNs":[93],"process":[94],"RF":[98],"data,":[99],"regression":[102],"produces":[104],"predictions":[105],"angle":[108],"after":[114],"layer.":[117],"To":[118],"show":[119],"performance":[121],"effectiveness":[123],"RF-assisted":[126],"method,":[127],"experimental":[129],"scenario":[130],"datasets":[132],"are":[133,137],"presented":[134],"experiments":[136],"then":[138],"discussed":[139],"along":[140],"results":[143],"that":[144],"have":[145],"been":[146],"obtained.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-09-13T00:00:00"}