{"id":"https://openalex.org/W4304892597","doi":null,"title":"Language-based audio retrieval with textual embeddings of tag names","display_name":"Language-based audio retrieval with textual embeddings of tag names","publication_year":2022,"publication_date":"2022-11-03","ids":{"openalex":"https://openalex.org/W4304892597"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-03812737v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-03812737v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://dcase.community/workshop2022/index","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03812737v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088037163","display_name":"Thomas Pellegrini","orcid":"https://orcid.org/0000-0001-8984-1399","observed_orcids":["https://orcid.org/0000-0001-8984-1399"]},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4210152422","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Pellegrini, Thomas","raw_affiliation_strings":["IRIT-SAMoVA - \u00c9quipe Structuration, Analyse et MOd\u00e9lisation de documents Vid\u00e9o et Audio (IRIT118 Route de Narbonne31062 Toulouse Cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IRIT-SAMoVA - \u00c9quipe Structuration, Analyse et MOd\u00e9lisation de documents Vid\u00e9o et Audio (IRIT118 Route de Narbonne31062 Toulouse Cedex 9 - France)","institution_ids":["https://openalex.org/I4210119061"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088037163"],"corresponding_institution_ids":["https://openalex.org/I4210119061"],"apc_list":null,"apc_paid":null,"fwci":0.3362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46309799,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"\u00e0 para\u00eetre","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":0.9976000189781189,"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":0.9976000189781189,"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":0.0008999999845400453,"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":0.0005000000237487257,"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/audio-embeddings","display_name":"audio embeddings","score":0.628000020980835},{"id":"https://openalex.org/keywords/text-embeddings","display_name":"text embeddings","score":0.656000018119812},{"id":"https://openalex.org/keywords/pre-trained-models","display_name":"pre-trained models","score":0.6499999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8422610759735107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6189882755279541},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4771537184715271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39041250944137573},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3457983732223511}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-03812737v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-03812737v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://dcase.community/workshop2022/index","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03812737v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-03812737v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://dcase.community/workshop2022/index","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4385749716","https://openalex.org/W4320167456","https://openalex.org/W7155397775","https://openalex.org/W7166806903","https://openalex.org/W3158978276","https://openalex.org/W4312069030","https://openalex.org/W4404577506","https://openalex.org/W4404519040","https://openalex.org/W4405021879","https://openalex.org/W4408795523"],"abstract_inverted_index":{"Language-based":[0],"audio":[1,6,67,72,112],"retrieval":[2],"aims":[3],"to":[4,30,65,142,149],"retrieve":[5],"recordings":[7],"based":[8,59],"on":[9,60,119,133],"a":[10,15,26,49,56,100],"queried":[11],"caption,":[12],"formulated":[13],"as":[14],"free-form":[16],"sentence":[17],"written":[18],"in":[19,46,99],"natural":[20],"language.":[21],"To":[22],"perform":[23],"this":[24,52,106],"task,":[25],"system":[27,58,107],"is":[28],"expected":[29],"project":[31],"both":[32],"modalities":[33],"(text":[34],"and":[35,68],"audio)":[36],"onto":[37],"the":[38,79,88,134,139],"same":[39],"subspace,":[40],"where":[41],"they":[42],"can":[43],"be":[44],"compared":[45,141],"terms":[47],"of":[48,81,87],"distance.":[50],"In":[51],"work,":[53],"we":[54,74],"propose":[55],"first":[57],"large":[61],"scale":[62],"pretrained":[63],"models":[64],"extract":[66],"text":[69,114],"embeddings.":[70,115],"As":[71],"embeddings,":[73],"use":[75],"logits":[76],"predicted":[77],"over":[78],"set":[80],"527":[82],"AudioSet":[83],"tag":[84,113],"categories,":[85],"instead":[86],"most":[89],"commonly":[90],"used":[91],"2-d":[92],"feature":[93],"maps":[94],"extracted":[95],"from":[96,111],"earlier":[97],"layers":[98],"deep":[101],"neural":[102],"network.":[103],"We":[104,145],"improved":[105],"by":[108],"adding":[109],"information":[110],"Experiments":[116],"were":[117],"conducted":[118],"Clotho":[120],"v2.":[121],"A":[122],"0.234":[123],"mean":[124],"average":[125],"precision":[126],"at":[127],"top":[128],"10":[129],"(mAP@10)":[130],"was":[131],"obtained":[132],"development-testing":[135],"split":[136],"when":[137],"using":[138],"tags,":[140],"0.229":[143],"without.":[144],"also":[146],"present":[147],"experiments":[148],"justify":[150],"our":[151],"architectural":[152],"design":[153],"choices":[154],"1":[155],".":[156]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2022-10-13T00:00:00"}