{"id":"https://openalex.org/W4283072444","doi":"https://doi.org/10.21437/odyssey.2022-54","title":"An Empirical Study of Weakly Supervised Audio Tagging Embeddings for General Audio Representations","display_name":"An Empirical Study of Weakly Supervised Audio Tagging Embeddings for General Audio Representations","publication_year":2022,"publication_date":"2022-06-17","ids":{"openalex":"https://openalex.org/W4283072444","doi":"https://doi.org/10.21437/odyssey.2022-54"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2022-54","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2022-54","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2022)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2209.15167","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080154283","display_name":"Heinrich Dinkel","orcid":"https://orcid.org/0000-0003-4330-8980"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Heinrich Dinkel","raw_affiliation_strings":["Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364004","display_name":"Zhiyong Yan","orcid":"https://orcid.org/0000-0003-3596-9463"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyong Yan","raw_affiliation_strings":["Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100673739","display_name":"Yongqing Wang","orcid":"https://orcid.org/0000-0003-1164-0137"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongqing Wang","raw_affiliation_strings":["Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362608","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0003-2335-0946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Corporation, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Corporation, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5080154283"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0566385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"390","last_page":"395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9993000030517578,"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/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7311868071556091},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44269368052482605},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4063414931297302},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3902851939201355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311868071556091},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44269368052482605},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4063414931297302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3902851939201355}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/odyssey.2022-54","is_oa":false,"landing_page_url":"https://doi.org/10.21437/odyssey.2022-54","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2022)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2209.15167","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.15167","pdf_url":"https://arxiv.org/pdf/2209.15167","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2209.15167","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2209.15167","pdf_url":"https://arxiv.org/pdf/2209.15167","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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2593116425","https://openalex.org/W2606176153","https://openalex.org/W2726515241","https://openalex.org/W2765407302","https://openalex.org/W2770119437","https://openalex.org/W2797583228","https://openalex.org/W2934177128","https://openalex.org/W2936774411","https://openalex.org/W2955425717","https://openalex.org/W2963163009","https://openalex.org/W2972584841","https://openalex.org/W2982343573","https://openalex.org/W3015949486","https://openalex.org/W3040498734","https://openalex.org/W3094550259","https://openalex.org/W3124216180","https://openalex.org/W3126565544","https://openalex.org/W3134486096","https://openalex.org/W3139878283","https://openalex.org/W3157916917","https://openalex.org/W3196974791","https://openalex.org/W3197580070","https://openalex.org/W3198882010","https://openalex.org/W3201143670","https://openalex.org/W3206996142","https://openalex.org/W4205689591","https://openalex.org/W4221095487","https://openalex.org/W4221150524","https://openalex.org/W4287757056","https://openalex.org/W4295312788","https://openalex.org/W4398958419"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W3204019825"],"abstract_inverted_index":{"We":[0,19],"study":[1],"the":[2,22,32],"usability":[3],"of":[4,24],"pre-trained":[5,42,76],"weakly":[6,40],"supervised":[7,41],"audio":[8,17],"tagging":[9],"(AT)":[10],"models":[11,43,77,94],"as":[12,53,101],"feature":[13,54],"extractors":[14],"for":[15,61,84],"general":[16],"representations.":[18],"mainly":[20],"analyze":[21],"feasibility":[23],"transferring":[25],"those":[26],"embeddings":[27],"to":[28,68],"other":[29],"tasks":[30,58,99],"within":[31],"speech":[33],"and":[34,45,87,104],"sound":[35],"domains.":[36],"Specifically,":[37],"we":[38],"benchmark":[39],"(MobileNetV2":[44],"EfficientNet-B0)":[46],"against":[47],"modern":[48],"self-supervised":[49],"learning":[50,82],"methods":[51],"(BYOL-A)":[52],"extractors.":[55],"Fourteen":[56],"downstream":[57],"are":[59,78],"used":[60],"evaluation":[62],"ranging":[63],"from":[64],"music":[65],"instrument":[66],"classification":[67],"language":[69],"classification.":[70,106],"Our":[71],"results":[72],"indicate":[73],"that":[74],"AT":[75,93],"an":[79],"excellent":[80],"transfer":[81],"choice":[83],"music,":[85],"event,":[86],"emotion":[88],"recognition":[89],"tasks.":[90],"Further,":[91],"finetuning":[92],"can":[95],"also":[96],"benefit":[97],"speech-related":[98],"such":[100],"keyword":[102],"spotting":[103],"intent":[105]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}