{"id":"https://openalex.org/W2995254904","doi":null,"title":"Deep Audio Priors Emerge From Harmonic Convolutional Networks","display_name":"Deep Audio Priors Emerge From Harmonic Convolutional Networks","publication_year":2020,"publication_date":"2020-04-30","ids":{"openalex":"https://openalex.org/W2995254904","mag":"2995254904"},"language":"en","primary_location":{"id":"mag:2995254904","doi":null,"is_oa":false,"landing_page_url":"https://www.openreview.net/pdf?id=rygjHxrYDB","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"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/A5066625739","display_name":"Zhoutong Zhang","orcid":"https://orcid.org/0000-0002-8144-1611","observed_orcids":["https://orcid.org/0000-0002-8144-1611"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhoutong Zhang","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714797","display_name":"Yunyun Wang","orcid":"https://orcid.org/0000-0002-0102-9898","observed_orcids":["https://orcid.org/0000-0002-0102-9898","https://orcid.org/0009-0006-3424-8057"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunyun Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0102-9898","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040877128","display_name":"Chuang Gan","orcid":"https://orcid.org/0000-0003-4031-5886","observed_orcids":["https://orcid.org/0000-0003-4031-5886"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chuang Gan","raw_affiliation_strings":["IBM (United States), Armonk, United States"],"raw_orcid":"https://orcid.org/0000-0003-4031-5886","affiliations":[{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621605","display_name":"Jiajun Wu","orcid":"https://orcid.org/0000-0002-4176-343X","observed_orcids":["https://orcid.org/0000-0002-4176-343X"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajun Wu","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071093940","display_name":"Joshua B. Tenenbaum","orcid":"https://orcid.org/0000-0002-1925-2035","observed_orcids":["https://orcid.org/0000-0002-1925-2035","https://orcid.org/0000-0002-0138-163X"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua B. Tenenbaum","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":"https://orcid.org/0000-0002-1925-2035","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085020955","display_name":"Antonio B. Torralba","orcid":"https://orcid.org/0000-0003-4915-0256","observed_orcids":["https://orcid.org/0000-0003-4915-0256"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Torralba","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, United States"],"raw_orcid":"https://orcid.org/0000-0003-4915-0256","affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074429265","display_name":"William T. Freeman","orcid":"https://orcid.org/0000-0002-2231-7995","observed_orcids":["https://orcid.org/0000-0002-2231-7995","https://orcid.org/0000-0002-3316-4007","https://orcid.org/0000-0001-9979-2500"]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William T. Freeman","raw_affiliation_strings":["Google (United States), Mountain View, United States"],"raw_orcid":"https://orcid.org/0000-0002-2231-7995","affiliations":[{"raw_affiliation_string":"Google (United States), Mountain View, United States","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9664,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.95409334,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9609000086784363,"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":0.9609000086784363,"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":0.03420000150799751,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.001500000013038516,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inductive-bias","display_name":"inductive bias","score":0.7990000247955322},{"id":"https://openalex.org/keywords/convolution-kernels","display_name":"convolution kernels","score":0.6340000033378601},{"id":"https://openalex.org/keywords/harmonic-series","display_name":"harmonic series","score":0.7210000157356262},{"id":"https://openalex.org/keywords/sound-source-separation","display_name":"sound source separation","score":0.9940000176429749},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.597000002861023},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"audio signal processing","score":0.6600000262260437}],"concepts":[{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.7842737436294556},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7574842572212219},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7158610224723816},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6770458221435547},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.586664617061615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5860597491264343},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5691937804222107},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.5172784328460693},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4784924387931824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44277650117874146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3836221694946289},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.339232861995697},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14640912413597107},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11260056495666504},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09160017967224121},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2995254904","doi":null,"is_oa":false,"landing_page_url":"https://www.openreview.net/pdf?id=rygjHxrYDB","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1969851134","https://openalex.org/W2012483839","https://openalex.org/W2078265833","https://openalex.org/W2099471712","https://openalex.org/W2117539524","https://openalex.org/W2130942839","https://openalex.org/W2153894152","https://openalex.org/W2163605009","https://openalex.org/W2184045248","https://openalex.org/W2194775991","https://openalex.org/W2502312327","https://openalex.org/W2519091744","https://openalex.org/W2584032004","https://openalex.org/W2654729393","https://openalex.org/W2773288354","https://openalex.org/W2779113761","https://openalex.org/W2805288670","https://openalex.org/W2807432252","https://openalex.org/W2810843531","https://openalex.org/W2887814324","https://openalex.org/W2902369404","https://openalex.org/W2931364255","https://openalex.org/W2941441145","https://openalex.org/W2941715400","https://openalex.org/W2946809691","https://openalex.org/W2962756039","https://openalex.org/W2962865004","https://openalex.org/W2962896155","https://openalex.org/W2963609956","https://openalex.org/W2964013315","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W3122887115"],"related_works":["https://openalex.org/W4297841477","https://openalex.org/W4387682234","https://openalex.org/W3153606321","https://openalex.org/W4293497932","https://openalex.org/W3015289235","https://openalex.org/W2941715400","https://openalex.org/W3160017072","https://openalex.org/W2757495192","https://openalex.org/W7027995731","https://openalex.org/W4378978442"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2,32,71,109],"(CNNs)":[3],"excel":[4],"in":[5,58,74,122],"image":[6,28],"recognition":[7],"and":[8,118],"generation.":[9],"Among":[10],"many":[11],"efforts":[12],"to":[13,91],"explain":[14],"their":[15],"effectiveness,":[16],"experiments":[17],"show":[18,45,55,107],"that":[19,25,46,68,108],"CNNs":[20],"carry":[21],"strong":[22,56],"inductive":[23,35],"biases":[24,36],"capture":[26],"natural":[27],"priors.":[29,61],"Do":[30],"deep":[31,70],"also":[33,131],"have":[34],"for":[37,50,103,136],"audio":[38,51,75,116,124],"signals?":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"empirically":[44],"current":[47],"network":[48],"architectures":[49],"processing":[52],"do":[53],"not":[54],"evidence":[57],"capturing":[59],"such":[60],"We":[62,106],"propose":[63],"Harmonic":[64,111,128],"Convolution,":[65,129],"an":[66],"operation":[67],"helps":[69],"distill":[72],"priors":[73,117],"signals":[76],"by":[77,87,94],"explicitly":[78],"utilizing":[79],"the":[80,89],"harmonic":[81,97],"structure":[82],"within.":[83],"This":[84],"is":[85],"done":[86],"engineering":[88],"kernel":[90],"be":[92],"supported":[93],"sets":[95],"of":[96,100],"series,":[98],"instead":[99],"local":[101],"neighborhoods":[102],"convolutional":[104],"kernels.":[105],"using":[110],"Convolution":[112],"can":[113],"reliably":[114],"model":[115],"achieve":[119,132],"high":[120],"performance":[121,135],"unsupervised":[123],"restoration":[125],"tasks.":[126],"With":[127],"they":[130],"better":[133],"generalization":[134],"sound":[137],"source":[138],"separation.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2019-12-26T00:00:00"}