{"id":"https://openalex.org/W2981182029","doi":"https://doi.org/10.1109/icassp40776.2020.9052990","title":"Clotho: an Audio Captioning Dataset","display_name":"Clotho: an Audio Captioning Dataset","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981182029","doi":"https://doi.org/10.1109/icassp40776.2020.9052990","mag":"2981182029"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9052990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.09387","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108358814","display_name":"Konstantinos Drossos","orcid":null},"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":"Konstantinos Drossos","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland","Tampere University,Audio Research Group,Tampere,Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Tampere University,Audio Research Group,Tampere,Finland","institution_ids":["https://openalex.org/I166825849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007748468","display_name":"Samuel Lipping","orcid":null},"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":"Samuel Lipping","raw_affiliation_strings":["Audio Research Group, Tampere University, Tampere, Finland","Tampere University,Audio Research Group,Tampere,Finland"],"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Tampere University,Audio Research Group,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":["Audio Research Group, Tampere University, Tampere, Finland","Tampere University"],"affiliations":[{"raw_affiliation_string":"Audio Research Group, Tampere University, Tampere, Finland","institution_ids":["https://openalex.org/I166825849"]},{"raw_affiliation_string":"Tampere University","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5108358814"],"corresponding_institution_ids":["https://openalex.org/I166825849"],"apc_list":null,"apc_paid":null,"fwci":0.14777568,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.38540501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"736","last_page":"740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.992900013923645,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9925000071525574,"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/closed-captioning","display_name":"Closed captioning","score":0.9520988464355469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8236905932426453},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6189005374908447},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5806179642677307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5659583210945129},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5126909017562866},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4642069935798645},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41105177998542786},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38584190607070923},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3245140016078949},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12178966403007507}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9520988464355469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8236905932426453},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6189005374908447},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5806179642677307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5659583210945129},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5126909017562866},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4642069935798645},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41105177998542786},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38584190607070923},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3245140016078949},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12178966403007507},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9052990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9052990","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.09387","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09387","pdf_url":"https://arxiv.org/pdf/1910.09387","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":null},{"id":"mag:2981182029","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.09387.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1910.09387","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.09387","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/dbgp-xm60","is_oa":true,"landing_page_url":"https://doi.org/10.17023/dbgp-xm60","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.09387","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.09387","pdf_url":"https://arxiv.org/pdf/1910.09387","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":null},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981182029.pdf","grobid_xml":"https://content.openalex.org/works/W2981182029.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W54887220","https://openalex.org/W1861492603","https://openalex.org/W2033875152","https://openalex.org/W2157331557","https://openalex.org/W2185175083","https://openalex.org/W2481240925","https://openalex.org/W2593116425","https://openalex.org/W2916103538","https://openalex.org/W2945761034","https://openalex.org/W2950635152","https://openalex.org/W2964121744","https://openalex.org/W2964213897","https://openalex.org/W2982554818","https://openalex.org/W6602203489","https://openalex.org/W6631190155","https://openalex.org/W6639102338"],"related_works":["https://openalex.org/W3015591594","https://openalex.org/W2945761034","https://openalex.org/W3047258309","https://openalex.org/W2024196298","https://openalex.org/W1255784701","https://openalex.org/W3176511664","https://openalex.org/W2059891914","https://openalex.org/W2752576222","https://openalex.org/W3160237369","https://openalex.org/W2792661572","https://openalex.org/W2874038628","https://openalex.org/W983516927","https://openalex.org/W2888994383","https://openalex.org/W2300150234","https://openalex.org/W2157391896","https://openalex.org/W2100730188","https://openalex.org/W1523612809","https://openalex.org/W2130164153","https://openalex.org/W31315099","https://openalex.org/W2970623693"],"abstract_inverted_index":{"Audio":[0],"captioning":[1,53],"is":[2,15,84,142],"the":[3,34,38,95,98,103,113],"novel":[4],"task":[5,19],"of":[6,40,55,59,69,97,107],"general":[7],"audio":[8,30,52,57,89],"content":[9,90],"description":[10,36],"using":[11,120],"free":[12],"text.":[13],"It":[14],"an":[16,27,29],"intermodal":[17],"translation":[18],"(not":[20],"speech-to-text),":[21],"where":[22],"a":[23,49,76],"system":[24],"accepts":[25],"as":[26],"input":[28],"signal":[31],"and":[32,65,75,91,94,116,124,134],"outputs":[33],"textual":[35],"(i.e.":[37],"caption)":[39],"that":[41],"signal.":[42],"In":[43],"this":[44],"paper":[45],"we":[46],"present":[47],"Clotho,":[48],"dataset":[50],"for":[51],"consisting":[54],"4981":[56],"samples":[58],"15":[60],"to":[61,71,79],"30":[62],"seconds":[63],"duration":[64],"24":[66],"905":[67],"captions":[68,117],"eight":[70],"20":[72],"words":[73],"length,":[74],"baseline":[77],"method":[78],"provide":[80],"initial":[81],"results.":[82],"Clotho":[83,141],"built":[85],"with":[86,139],"focus":[87],"on":[88],"caption":[92],"diversity,":[93],"splits":[96],"data":[99],"are":[100,111,118,137],"not":[101],"hampering":[102],"training":[104],"or":[105],"evaluation":[106],"methods.":[108],"All":[109],"sounds":[110],"from":[112,126],"Freesound":[114],"platform,":[115],"crowdsourced":[119],"Amazon":[121],"Mechanical":[122],"Turk":[123],"annotators":[125],"English":[127],"speaking":[128],"countries.":[129],"Unique":[130],"words,":[131],"named":[132],"entities,":[133],"speech":[135],"transcription":[136],"removed":[138],"post-processing.":[140],"freely":[143],"available":[144],"online":[145],"(https://zenodo.org/record/3490684).":[146]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
