{"id":"https://openalex.org/W4304099145","doi":"https://doi.org/10.1145/3503161.3551579","title":"Masked Modeling-based Audio Representation for ACM Multimedia 2022 Computational Paralinguistics ChallengE","display_name":"Masked Modeling-based Audio Representation for ACM Multimedia 2022 Computational Paralinguistics ChallengE","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304099145","doi":"https://doi.org/10.1145/3503161.3551579"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3551579","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551579","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5005516309","display_name":"Kang Soo You","orcid":"https://orcid.org/0009-0009-5685-2521"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang You","raw_affiliation_strings":["National University of Defense Technology, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Shanghai, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018669598","display_name":"Boqing Zhu","orcid":"https://orcid.org/0000-0001-7867-2112"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boqing Zhu","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103019832","display_name":"Feng Ming","orcid":"https://orcid.org/0000-0001-7995-615X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Feng","raw_affiliation_strings":["National University of Defense Technology, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Shanghai, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039795290","display_name":"Dawei Feng","orcid":"https://orcid.org/0000-0002-7587-8905"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Feng","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461596","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0001-8140-2279"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101740892","display_name":"Tian Gao","orcid":"https://orcid.org/0000-0003-2142-9124"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Gao","raw_affiliation_strings":["National University of Defense Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Hefei, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088885490","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0002-1236-8318"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7060","last_page":"7064"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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":0.9973999857902527,"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":0.991599977016449,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9914000034332275,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.8486930727958679},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7274790406227112},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6690348386764526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5675909519195557},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5397712588310242},{"id":"https://openalex.org/keywords/pretext","display_name":"Pretext","score":0.4864049255847931},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.44414448738098145},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4404072165489197},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4389280080795288},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4315081536769867},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3722723126411438},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34963443875312805},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3060300350189209}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8486930727958679},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7274790406227112},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6690348386764526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5675909519195557},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5397712588310242},{"id":"https://openalex.org/C2779627259","wikidata":"https://www.wikidata.org/wiki/Q779763","display_name":"Pretext","level":3,"score":0.4864049255847931},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44414448738098145},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4404072165489197},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4389280080795288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4315081536769867},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3722723126411438},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34963443875312805},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3060300350189209},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3551579","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3551579","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W3138516171","https://openalex.org/W4212774754","https://openalex.org/W4304098636"],"related_works":["https://openalex.org/W4360764600","https://openalex.org/W2289868279","https://openalex.org/W2793814466","https://openalex.org/W1546240199","https://openalex.org/W2109142991","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,34,85],"present":[4],"our":[5,100],"solution":[6],"for":[7,46],"ACM":[8],"Multimedia":[9],"2022":[10],"Computational":[11],"Paralinguistics":[12],"Challenge.":[13],"Our":[14],"method":[15],"employs":[16],"the":[17,38,47,55,62,68,73,76,82,87,92,97],"self-supervised":[18],"learning":[19],"paradigm,":[20],"as":[21],"it":[22],"achieves":[23],"promising":[24],"results":[25],"in":[26],"computer":[27],"vision":[28],"and":[29,78],"audio":[30,48],"signal":[31],"processing.":[32],"Specifically,":[33],"firstly":[35],"explore":[36],"modifying":[37],"Swin":[39],"Transformer":[40],"architecture":[41],"to":[42,66,90],"learn":[43],"general":[44],"representation":[45],"signals,":[49],"accompanied":[50],"with":[51,96],"random":[52],"masking":[53],"on":[54],"log-mel":[56],"spectrogram.":[57],"The":[58],"main":[59],"goal":[60],"of":[61,75],"pretext":[63],"task":[64],"is":[65],"predict":[67],"masked":[69,79],"parts,":[70],"by":[71],"combining":[72],"advantages":[74],"Swin-Transformer":[77],"modeling.":[80],"For":[81],"downstream":[83],"tasks,":[84],"utilize":[86],"labelled":[88],"datasets":[89],"fine-tune":[91],"pre-trained":[93],"model.":[94],"Compared":[95],"competitive":[98],"baselines,":[99],"approach":[101],"can":[102],"provide":[103],"significant":[104],"performance":[105],"improvements":[106],"without":[107],"ensembling.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}