{"id":"https://openalex.org/W4387882781","doi":"https://doi.org/10.1109/mlsp55844.2023.10285891","title":"A Multitask Learning Approach For Sound Source Tracking With Icosahedral Convolutional Neural Networks","display_name":"A Multitask Learning Approach For Sound Source Tracking With Icosahedral Convolutional Neural Networks","publication_year":2023,"publication_date":"2023-09-17","ids":{"openalex":"https://openalex.org/W4387882781","doi":"https://doi.org/10.1109/mlsp55844.2023.10285891"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp55844.2023.10285891","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mlsp55844.2023.10285891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},"type":"article","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/A5101760078","display_name":"Eduardo Alves da Silva","orcid":"https://orcid.org/0000-0001-6849-8165"},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Eduardo Alves Da Silva","raw_affiliation_strings":["Federal University of Rio de Janeiro (UFRJ),Rio de Janeiro,Brazil","Federal University of Rio de Janeiro (UFRJ), Rio de Janeiro, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Rio de Janeiro (UFRJ),Rio de Janeiro,Brazil","institution_ids":["https://openalex.org/I122140584"]},{"raw_affiliation_string":"Federal University of Rio de Janeiro (UFRJ), Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114038133","display_name":"Luiz Wagner Pereira Biscainho","orcid":null},"institutions":[{"id":"https://openalex.org/I122140584","display_name":"Universidade Federal do Rio de Janeiro","ror":"https://ror.org/03490as77","country_code":"BR","type":"education","lineage":["https://openalex.org/I122140584"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Luiz Wagner Pereira Biscainho","raw_affiliation_strings":["Federal University of Rio de Janeiro (UFRJ),Rio de Janeiro,Brazil","Federal University of Rio de Janeiro (UFRJ), Rio de Janeiro, Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Rio de Janeiro (UFRJ),Rio de Janeiro,Brazil","institution_ids":["https://openalex.org/I122140584"]},{"raw_affiliation_string":"Federal University of Rio de Janeiro (UFRJ), Rio de Janeiro, Brazil","institution_ids":["https://openalex.org/I122140584"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101760078"],"corresponding_institution_ids":["https://openalex.org/I122140584"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14320586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11698","display_name":"Underwater Acoustics Research","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1910","display_name":"Oceanography"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9919999837875366,"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/autoencoder","display_name":"Autoencoder","score":0.8042215704917908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7413228154182434},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6592628955841064},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6469744443893433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6382666826248169},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.537559449672699},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5104843378067017},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4638414978981018},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3343323767185211}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8042215704917908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7413228154182434},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6592628955841064},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6469744443893433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6382666826248169},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.537559449672699},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5104843378067017},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4638414978981018},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3343323767185211}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mlsp55844.2023.10285891","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mlsp55844.2023.10285891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1555217905","https://openalex.org/W1745334888","https://openalex.org/W1844783403","https://openalex.org/W2046317813","https://openalex.org/W2061074721","https://openalex.org/W2336416123","https://openalex.org/W2591917595","https://openalex.org/W2898268964","https://openalex.org/W2913340405","https://openalex.org/W2914520121","https://openalex.org/W3031005739","https://openalex.org/W3034751264","https://openalex.org/W3094079453","https://openalex.org/W3094174670","https://openalex.org/W3104196160","https://openalex.org/W3108495681","https://openalex.org/W3157286395","https://openalex.org/W3160649118","https://openalex.org/W3197097128","https://openalex.org/W4224932505","https://openalex.org/W4310863306","https://openalex.org/W4313034353","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6794315554","https://openalex.org/W6842324833"],"related_works":["https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W4392946183","https://openalex.org/W3088732000","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3167935049"],"abstract_inverted_index":{"Many":[0],"different":[1],"modern":[2],"applications":[3],"require":[4],"systems":[5],"that":[6],"are":[7,100],"able":[8,109],"to":[9,110,123],"track":[10],"sound":[11],"sources.":[12],"To":[13,41],"this":[14,27],"end,":[15],"recent":[16],"methodologies":[17],"combine":[18],"microphone":[19],"array":[20],"signal":[21],"processing":[22],"with":[23],"deep":[24],"learning.":[25],"In":[26,74],"paper,":[28],"a":[29,46,66,78,112],"new":[30,44],"technique":[31],"for":[32,49,69,81],"neural":[33,60],"network":[34],"training":[35,72],"using":[36],"multitask":[37],"learning":[38],"is":[39],"proposed.":[40],"illustrate":[42],"the":[43,70,75,124],"approach,":[45],"state-of-the-art":[47],"architecture":[48],"source":[50],"direction":[51],"of":[52],"arrival":[53],"(DOA)":[54],"tracking":[55],"based":[56],"on":[57],"icosahedral":[58,84],"convolutional":[59],"networks":[61,99],"(icoCNN)":[62],"was":[63,86,108],"taken":[64],"as":[65],"starting":[67],"point":[68],"novel":[71],"method.":[73],"proposed":[76],"strategy,":[77],"deconvolutional":[79],"layer":[80],"hexagonal":[82],"grid":[83],"maps":[85],"employed":[87],"in":[88,93,102,115],"an":[89],"autoencoder":[90],"pre-training":[91],"stage,":[92],"which":[94],"SNR":[95],"and":[96],"T60":[97],"classification":[98],"trained":[101],"parallel.":[103],"The":[104],"AutoEncoder+icoCNN":[105],"(AEicoCNN)":[106],"combination":[107],"achieve":[111],"6%":[113],"reduction":[114],"root":[116],"mean":[117],"square":[118],"angular":[119],"error":[120],"when":[121],"compared":[122],"regular":[125],"icoCNN":[126],"training.":[127]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}