{"id":"https://openalex.org/W3149712154","doi":"https://doi.org/10.1109/taslp.2021.3069193","title":"Ambisonic Signal Processing DNNs Guaranteeing Rotation, Scale and Time Translation Equivariance","display_name":"Ambisonic Signal Processing DNNs Guaranteeing Rotation, Scale and Time Translation Equivariance","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3149712154","doi":"https://doi.org/10.1109/taslp.2021.3069193","mag":"3149712154"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3069193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3069193","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5060365760","display_name":"R. Sato","orcid":"https://orcid.org/0000-0001-8914-4905"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryotaro Sato","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Nippon Telegraph and Telephone Corporation, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8914-4905","affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Nippon Telegraph and Telephone Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046170826","display_name":"Kenta Niwa","orcid":"https://orcid.org/0000-0002-6911-0238"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenta Niwa","raw_affiliation_strings":["NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Kyoto, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6911-0238","affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109046289","display_name":"Kazunori Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Kobayashi","raw_affiliation_strings":["NTT Media Intelligence Laboratories, Nippon Telegraph and Telephone Corporation, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, Nippon Telegraph and Telephone Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":0.5629,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.6413184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"29","issue":null,"first_page":"1449","last_page":"1462"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6524116396903992},{"id":"https://openalex.org/keywords/rotation","display_name":"Rotation (mathematics)","score":0.6272976994514465},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.6145559549331665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5629838109016418},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5183807015419006},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.43658921122550964},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38657933473587036},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34520938992500305},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33016467094421387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30468985438346863},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.13398054242134094},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09932336211204529},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.09878286719322205},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07433241605758667},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.06332162022590637}],"concepts":[{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6524116396903992},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.6272976994514465},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.6145559549331665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5629838109016418},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5183807015419006},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.43658921122550964},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38657933473587036},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34520938992500305},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33016467094421387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30468985438346863},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.13398054242134094},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09932336211204529},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.09878286719322205},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07433241605758667},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.06332162022590637},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2021.3069193","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3069193","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W197865394","https://openalex.org/W1522301498","https://openalex.org/W1551148884","https://openalex.org/W1625053673","https://openalex.org/W1836465849","https://openalex.org/W1847162973","https://openalex.org/W1945616565","https://openalex.org/W1984948727","https://openalex.org/W2098795429","https://openalex.org/W2112796928","https://openalex.org/W2145860534","https://openalex.org/W2147996290","https://openalex.org/W2149648624","https://openalex.org/W2162931300","https://openalex.org/W2205176333","https://openalex.org/W2279221249","https://openalex.org/W2408239454","https://openalex.org/W2519091744","https://openalex.org/W2594251744","https://openalex.org/W2774389566","https://openalex.org/W2783784437","https://openalex.org/W2785397276","https://openalex.org/W2786625961","https://openalex.org/W2788775653","https://openalex.org/W2796422723","https://openalex.org/W2810934215","https://openalex.org/W2900935497","https://openalex.org/W2914520121","https://openalex.org/W2917254586","https://openalex.org/W2938901746","https://openalex.org/W2946332576","https://openalex.org/W2952241957","https://openalex.org/W2962748579","https://openalex.org/W2962913459","https://openalex.org/W2963128891","https://openalex.org/W2963207607","https://openalex.org/W2963297642","https://openalex.org/W2963429797","https://openalex.org/W2963452667","https://openalex.org/W2963504932","https://openalex.org/W2963737468","https://openalex.org/W2964121744","https://openalex.org/W2964213081","https://openalex.org/W2982382207","https://openalex.org/W2982680886","https://openalex.org/W3030781580","https://openalex.org/W3035684957","https://openalex.org/W3047232705","https://openalex.org/W3105684037","https://openalex.org/W4213223317","https://openalex.org/W4236344233","https://openalex.org/W4243055393","https://openalex.org/W4287864501","https://openalex.org/W4297688279","https://openalex.org/W4300658615","https://openalex.org/W4301369164","https://openalex.org/W6608057492","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6640425456","https://openalex.org/W6674591210","https://openalex.org/W6678878334","https://openalex.org/W6682325752","https://openalex.org/W6683965311","https://openalex.org/W6694954494","https://openalex.org/W6738884980","https://openalex.org/W6747473890","https://openalex.org/W6748461236","https://openalex.org/W6748579715","https://openalex.org/W6749031613","https://openalex.org/W6750239584","https://openalex.org/W6751512325","https://openalex.org/W6752766600","https://openalex.org/W6752979358","https://openalex.org/W6759134542","https://openalex.org/W6769516661","https://openalex.org/W6774448971"],"related_works":["https://openalex.org/W2067549729","https://openalex.org/W2382412288","https://openalex.org/W1986190647","https://openalex.org/W2401401198","https://openalex.org/W2059569368","https://openalex.org/W3135923011","https://openalex.org/W2077788825","https://openalex.org/W2989915422","https://openalex.org/W2042136086","https://openalex.org/W2353089562"],"abstract_inverted_index":{"We":[0,180],"propose":[1,181],"a":[2,87,182,221],"novel":[3],"framework":[4],"to":[5,31,132,142,199],"design":[6,185,220],"Ambisonic":[7,232],"signal":[8,22,62,91],"processing":[9,23,63],"deep":[10],"neural":[11],"networks":[12],"(DNNs)":[13],"that":[14,237],"guarantee":[15],"physical":[16],"symmetries.":[17],"In":[18,157],"general,":[19],"spatial":[20,244],"acoustic":[21,135],"DNNs":[24],"for,":[25],"e.g.,":[26,116],"sound":[27,44,125,225],"event":[28,226],"detection,":[29],"ought":[30],"perform":[32,103],"with":[33,86,190],"the":[34,39,73,98,106,117,120,124,155,171],"equivalent":[35],"accuracy":[36],"regardless":[37],"of":[38,41,43,90,119,123,154,173,204,216],"directions":[40,122],"arrival":[42],"sources.":[45],"This":[46],"property":[47],"is":[48,109,127,140,240],"well":[49],"known":[50],"as":[51,148],"rotation":[52,65,78],"symmetry":[53,66,79,164],"in":[54,58,130,137,170],"natural":[55],"science.":[56],"However,":[57],"most":[59],"conventional":[60,99],"multichannel":[61],"DNNs,":[64,138],"has":[67,80],"not":[68,102],"been":[69,81],"explicitly":[70],"incorporated":[71],"into":[72],"model":[74,223,239],"structure,":[75],"and":[76,151,192,210,228],"pseudo":[77],"acquired":[82],"by":[83],"training":[84,107],"models":[85],"large":[88],"amount":[89],"datasets":[92],"arriving":[93,121],"from":[94,231],"various":[95],"directions.":[96],"Therefore,":[97],"methods":[100],"will":[101],"sufficiently":[104],"when":[105],"dataset":[108],"relatively":[110],"small":[111],"scale":[112],"or":[113],"statistically":[114],"biased,":[115],"distribution":[118],"events":[126],"inhomogeneous.":[128],"Furthermore,":[129],"order":[131],"efficiently":[133],"handle":[134],"signals":[136],"it":[139],"necessary":[141],"consider":[143],"several":[144],"additional":[145],"symmetries,":[146],"such":[147],"amplitude":[149,208],"scaling":[150],"time":[152,211],"translation":[153,194],"signals.":[156,233],"this":[158,217,238],"paper,":[159],"we":[160,219],"integratedly":[161],"formulate":[162],"these":[163],"assumptions,":[165],"which":[166,197],"are":[167],"called":[168,187],"equivariance,":[169],"form":[172],"constraints":[174],"for":[175,224,246],"our":[176],"targeted":[177],"DNN":[178,184,222],"design.":[179],"new":[183],"method":[186],"Clebsch-Gordan":[188],"Nets":[189],"Scale":[191],"Time":[193],"Symmetry":[195],"(CGNets-STS),":[196],"guarantees":[198],"simultaneously":[200],"satisfy":[201],"three":[202],"types":[203],"equivariance":[205],"(3D":[206],"rotation,":[207],"scaling,":[209],"translation).":[212],"As":[213],"an":[214],"instance":[215],"method,":[218],"localization":[227],"detection":[229],"tasks":[230],"Experimental":[234],"results":[235],"show":[236],"highly":[241],"robust":[242],"against":[243],"rotations":[245],"input":[247],"data.":[248]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}