{"id":"https://openalex.org/W3138521398","doi":"https://doi.org/10.1109/taslp.2021.3065234","title":"Zero-Shot Audio Classification Via Semantic Embeddings","display_name":"Zero-Shot Audio Classification Via Semantic Embeddings","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3138521398","doi":"https://doi.org/10.1109/taslp.2021.3065234","mag":"3138521398"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3065234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3065234","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/A5103228867","display_name":"Huang Xie","orcid":"https://orcid.org/0000-0001-7609-8049"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Huang Xie","raw_affiliation_strings":["Faculty of Information Technology, and Communication Sciences, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Faculty of Information Technology, and Communication Sciences, Tampere University, Tampere, Finland"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, and Communication Sciences, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103228867"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":5.6863,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.9687458,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"1233","last_page":"1242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9962000250816345,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9631999731063843,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7413020133972168},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.7217293977737427},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5544973015785217},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5501148104667664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5124288201332092},{"id":"https://openalex.org/keywords/word2vec","display_name":"Word2vec","score":0.4961879849433899},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4435189962387085},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4168604016304016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7413020133972168},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.7217293977737427},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5544973015785217},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5501148104667664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5124288201332092},{"id":"https://openalex.org/C2776461190","wikidata":"https://www.wikidata.org/wiki/Q22673982","display_name":"Word2vec","level":3,"score":0.4961879849433899},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4435189962387085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4168604016304016}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2021.3065234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3065234","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"},{"id":"pmh:oai:trepo.tuni.fi:10024/217857","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/217857","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2327472798","display_name":null,"funder_award_id":"637422","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"}],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W21006490","https://openalex.org/W652269744","https://openalex.org/W1522301498","https://openalex.org/W1614298861","https://openalex.org/W1686810756","https://openalex.org/W1865725639","https://openalex.org/W1987063155","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2108598243","https://openalex.org/W2109244020","https://openalex.org/W2128532956","https://openalex.org/W2150295085","https://openalex.org/W2153579005","https://openalex.org/W2162489814","https://openalex.org/W2171061940","https://openalex.org/W2250539671","https://openalex.org/W2289084343","https://openalex.org/W2334493732","https://openalex.org/W2398243923","https://openalex.org/W2509065397","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2604763608","https://openalex.org/W2770119437","https://openalex.org/W2783837693","https://openalex.org/W2896457183","https://openalex.org/W2930959424","https://openalex.org/W2954224973","https://openalex.org/W2962835968","https://openalex.org/W2962999716","https://openalex.org/W2963341956","https://openalex.org/W2963499153","https://openalex.org/W2964086552","https://openalex.org/W2964121744","https://openalex.org/W2990796920","https://openalex.org/W2998351764","https://openalex.org/W3015337773","https://openalex.org/W3015474227","https://openalex.org/W3034942609","https://openalex.org/W3091905774","https://openalex.org/W3098357269","https://openalex.org/W4294170691","https://openalex.org/W6600827882","https://openalex.org/W6631190155","https://openalex.org/W6636510571","https://openalex.org/W6637373629","https://openalex.org/W6682222085","https://openalex.org/W6682691769","https://openalex.org/W6712594816","https://openalex.org/W6736057607","https://openalex.org/W6746278845","https://openalex.org/W6755207826","https://openalex.org/W6765174816","https://openalex.org/W6783596713"],"related_works":["https://openalex.org/W2980729574","https://openalex.org/W1560851690","https://openalex.org/W3092047717","https://openalex.org/W4390881630","https://openalex.org/W2770162183","https://openalex.org/W3110772647","https://openalex.org/W2947721150","https://openalex.org/W2894231409","https://openalex.org/W3127365535","https://openalex.org/W2597655663"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,177],"study":[4],"zero-shot":[5,189],"learning":[6],"in":[7,174],"audio":[8,35,66,86,148],"classification":[9,113,157],"via":[10],"semantic":[11,48,75,130],"embeddings":[12,73,84,99,105,182,185,198],"extracted":[13],"from":[14,85,100,106],"textual":[15,101],"labels":[16,102],"and":[17,68,74,88,128,144,183],"sentence":[18,104,107,184],"descriptions":[19,108],"of":[20,33,37,65,109,150],"sound":[21,38,69,110,164],"classes.":[22,111],"Our":[23],"goal":[24],"is":[25,31,114,159,193],"to":[26,57,80,95,170],"obtain":[27],"a":[28,53,117,129,139,145],"classifier":[29],"that":[30,40,121,156,166,179],"capable":[32],"recognizing":[34],"instances":[36,67],"classes":[39,165,173],"have":[41],"no":[42],"available":[43],"training":[44],"samples,":[45],"but":[46],"only":[47],"side":[49],"information.":[50],"We":[51,77,133],"employ":[52],"bilinear":[54],"compatibility":[55,119],"framework":[56],"learn":[58],"an":[59,125],"acoustic-semantic":[60],"projection":[61],"between":[62],"intermediate-level":[63],"representations":[64],"classes,":[70],"i.e.,":[71],"acoustic":[72,83,126],"embeddings.":[76],"use":[78],"VGGish":[79],"extract":[81],"deep":[82],"clips,":[87],"pre-trained":[89],"language":[90,202],"models":[91],"(Word2Vec,":[92],"GloVe,":[93],"BERT)":[94],"generate":[96],"either":[97],"label":[98,181],"or":[103],"Audio":[112],"performed":[115],"by":[116,162,195],"linear":[118],"function":[120],"measures":[122],"how":[123],"compatible":[124],"embedding":[127,131],"are.":[132],"evaluate":[134],"the":[135,171,208],"proposed":[136],"method":[137],"on":[138],"small":[140],"balanced":[141],"dataset":[142],"ESC-50":[143],"large-scale":[146],"unbalanced":[147],"subset":[149],"AudioSet.":[151],"The":[152],"experimental":[153],"results":[154,209],"show":[155],"performance":[158,192],"significantly":[160],"improved":[161,194,211],"involving":[163],"are":[167,186,210],"semantically":[168],"close":[169],"test":[172],"training.":[175],"Meanwhile,":[176],"demonstrate":[178],"both":[180],"useful":[187],"for":[188],"learning.":[190],"Classification":[191],"concatenating":[196],"label/sentence":[197],"generated":[199],"with":[200],"different":[201],"models.":[203],"With":[204],"their":[205],"hybrid":[206],"concatenations,":[207],"further.":[212]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}