{"id":"https://openalex.org/W4408355688","doi":"https://doi.org/10.1109/icassp49660.2025.10887869","title":"Gen-A: Generalizing Ambisonics Neural Encoding to Unseen Microphone Arrays","display_name":"Gen-A: Generalizing Ambisonics Neural Encoding to Unseen Microphone Arrays","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355688","doi":"https://doi.org/10.1109/icassp49660.2025.10887869"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5078854716","display_name":"Mikko Heikkinen","orcid":"https://orcid.org/0000-0001-9898-1916"},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Mikko Heikkinen","raw_affiliation_strings":["Nokia Technologies,Tampere,Finland"],"affiliations":[{"raw_affiliation_string":"Nokia Technologies,Tampere,Finland","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010846139","display_name":"Archontis Politis","orcid":"https://orcid.org/0000-0002-0595-2356"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Archontis Politis","raw_affiliation_strings":["Tampere University,Tampere,Finland"],"affiliations":[{"raw_affiliation_string":"Tampere University,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108358814","display_name":"Konstantinos Drossos","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Konstantinos Drossos","raw_affiliation_strings":["Nokia Technologies,Tampere,Finland"],"affiliations":[{"raw_affiliation_string":"Nokia Technologies,Tampere,Finland","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Nokia Technologies,Espoo,Finland"],"affiliations":[{"raw_affiliation_string":"Nokia Technologies,Espoo,Finland","institution_ids":["https://openalex.org/I2738502077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078854716"],"corresponding_institution_ids":["https://openalex.org/I2738502077"],"apc_list":null,"apc_paid":null,"fwci":3.8348,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.92245086,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9912999868392944,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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":0.9064267873764038},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7890676856040955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6848855018615723},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6021292209625244},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48033037781715393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4558407962322235},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36458247900009155},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3446614146232605},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.12262904644012451},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11736628413200378},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05547451972961426}],"concepts":[{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.9064267873764038},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7890676856040955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6848855018615723},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6021292209625244},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48033037781715393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4558407962322235},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36458247900009155},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3446614146232605},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.12262904644012451},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11736628413200378},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05547451972961426},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","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/icassp49660.2025.10887869","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887869","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/232763","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/232763","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"conference"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2052666245","https://openalex.org/W2068815893","https://openalex.org/W2089473323","https://openalex.org/W2494085323","https://openalex.org/W2654615262","https://openalex.org/W2763188033","https://openalex.org/W2772289775","https://openalex.org/W2962935966","https://openalex.org/W2972951785","https://openalex.org/W4214652421","https://openalex.org/W4236344233","https://openalex.org/W4285294643","https://openalex.org/W4312384165","https://openalex.org/W4372259804","https://openalex.org/W4392903617","https://openalex.org/W4403126678","https://openalex.org/W6632948751","https://openalex.org/W7046848240"],"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/W1571600724","https://openalex.org/W2897160306","https://openalex.org/W2604047122","https://openalex.org/W107154053","https://openalex.org/W2487629029"],"abstract_inverted_index":{"Using":[0],"deep":[1],"neural":[2],"networks":[3],"(DNNs)":[4],"for":[5,35,44,77,119,123],"encoding":[6,46,113],"of":[7,22,74],"microphone":[8],"array":[9],"(MA)":[10],"signals":[11,67],"to":[12,31,50],"the":[13,62,86,115,126],"Ambisonics":[14,45],"spatial":[15],"audio":[16],"format":[17],"can":[18,48],"surpass":[19],"certain":[20],"limitations":[21],"established":[23],"conventional":[24,112],"methods,":[25],"but":[26],"existing":[27],"DNN-based":[28,42],"methods":[29],"need":[30],"be":[32],"trained":[33],"separately":[34],"each":[36,90],"MA.":[37],"This":[38],"paper":[39],"proposes":[40],"a":[41,70],"method":[43,58,93],"that":[47],"generalize":[49],"arbitrary":[51],"MA":[52,63,66],"geometries":[53],"unseen":[54],"during":[55],"training.":[56],"The":[57,92,107],"takes":[59],"as":[60],"inputs":[61],"geometry":[64,78,83],"and":[65,68,79,99,104],"uses":[69],"multi-level":[71],"encoder":[72,88],"consisting":[73],"separate":[75],"paths":[76],"signal":[80,87],"data,":[81],"where":[82],"features":[84],"inform":[85],"at":[89],"level.":[91],"is":[94,128],"validated":[95],"in":[96],"simulated":[97],"anechoic":[98],"reverberant":[100,124],"conditions":[101],"with":[102],"one":[103],"two":[105],"sources.":[106],"results":[108],"indicate":[109],"improvement":[110,127],"over":[111],"across":[114],"whole":[116],"frequency":[117],"range":[118],"dry":[120],"scenes,":[121],"while":[122],"scenes":[125],"frequency-dependent.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
