{"id":"https://openalex.org/W4285483774","doi":"https://doi.org/10.48550/arxiv.2207.06405","title":"Masked Autoencoders that Listen","display_name":"Masked Autoencoders that Listen","publication_year":2022,"publication_date":"2022-07-13","ids":{"openalex":"https://openalex.org/W4285483774","doi":"https://doi.org/10.48550/arxiv.2207.06405"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2207.06405","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.06405","pdf_url":"https://arxiv.org/pdf/2207.06405","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2207.06405","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063149046","display_name":"Po-Yao Huang","orcid":"https://orcid.org/0000-0002-3319-5145"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Huang, Po-Yao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385219","display_name":"Xu Hu","orcid":"https://orcid.org/0000-0002-6345-2448"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Hu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Juncheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031979802","display_name":"Alexei Baevski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baevski, Alexei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083212922","display_name":"Michael Auli","orcid":"https://orcid.org/0000-0001-5974-4459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Auli, Michael","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022540761","display_name":"Wojciech Galuba","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Galuba, Wojciech","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Metze, Florian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036069974","display_name":"Christoph Feichtenhofer","orcid":"https://orcid.org/0000-0001-9756-7238"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feichtenhofer, Christoph","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5063149046"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":109,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9988999962806702,"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":0.9988999962806702,"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":0.9987999796867371,"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":0.9797999858856201,"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/spectrogram","display_name":"Spectrogram","score":0.935533881187439},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7801512479782104},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7788214683532715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6754748821258545},{"id":"https://openalex.org/keywords/decodes","display_name":"Decodes","score":0.5491575598716736},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4902086853981018},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4472023546695709},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4201125502586365},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.39558809995651245},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38939574360847473},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13872110843658447}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.935533881187439},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7801512479782104},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7788214683532715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6754748821258545},{"id":"https://openalex.org/C2778858076","wikidata":"https://www.wikidata.org/wiki/Q5249539","display_name":"Decodes","level":3,"score":0.5491575598716736},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4902086853981018},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4472023546695709},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4201125502586365},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.39558809995651245},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38939574360847473},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13872110843658447},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2207.06405","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.06405","pdf_url":"https://arxiv.org/pdf/2207.06405","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2207.06405","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2207.06405","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2207.06405","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.06405","pdf_url":"https://arxiv.org/pdf/2207.06405","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2544616823","https://openalex.org/W1982067419","https://openalex.org/W1967913462","https://openalex.org/W2355552759","https://openalex.org/W1993624831","https://openalex.org/W2996640127","https://openalex.org/W1769898127","https://openalex.org/W2155299007","https://openalex.org/W3114514296"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"a":[3,33,95],"simple":[4],"extension":[5],"of":[6],"image-based":[7],"Masked":[8],"Autoencoders":[9],"(MAE)":[10],"to":[11,60,69],"self-supervised":[12],"representation":[13],"learning":[14],"from":[15],"audio":[16,29,78,110],"spectrograms.":[17],"Following":[18],"the":[19,39,51,62,75,92],"Transformer":[20],"encoder-decoder":[21],"design":[22],"in":[23,58,74,83],"MAE,":[24],"our":[25],"Audio-MAE":[26,103],"first":[27],"encodes":[28],"spectrogram":[30],"patches":[31],"with":[32,55,94],"high":[34],"masking":[35,97],"ratio,":[36],"feeding":[37],"only":[38],"non-masked":[40],"tokens":[41],"through":[42],"encoder":[43,93],"layers.":[44],"The":[45,124],"decoder":[46],"then":[47,90],"re-orders":[48],"and":[49,86,111,126],"decodes":[50],"encoded":[52],"context":[53],"padded":[54],"mask":[56],"tokens,":[57],"order":[59],"reconstruct":[61],"input":[63],"spectrogram.":[64],"We":[65,89],"find":[66],"it":[67],"beneficial":[68],"incorporate":[70],"local":[71,84],"window":[72],"attention":[73],"decoder,":[76],"as":[77],"spectrograms":[79],"are":[80],"highly":[81],"correlated":[82],"time":[85],"frequency":[87],"bands.":[88],"fine-tune":[91],"lower":[96],"ratio":[98],"on":[99,108],"target":[100],"datasets.":[101],"Empirically,":[102],"sets":[104],"new":[105],"state-of-the-art":[106],"performance":[107],"six":[109],"speech":[112],"classification":[113],"tasks,":[114],"outperforming":[115],"other":[116],"recent":[117],"models":[118,127],"that":[119],"use":[120],"external":[121],"supervised":[122],"pre-training.":[123],"code":[125],"will":[128],"be":[129],"at":[130],"https://github.com/facebookresearch/AudioMAE.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":39},{"year":2023,"cited_by_count":47},{"year":2022,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}