{"id":"https://openalex.org/W4393840460","doi":"https://doi.org/10.5281/zenodo.1495070","title":"Synthetically Spoken STAIR","display_name":"Synthetically Spoken STAIR","publication_year":2018,"publication_date":"2018-11-23","ids":{"openalex":"https://openalex.org/W4393840460","doi":"https://doi.org/10.5281/zenodo.1495070"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:1495070","is_oa":true,"landing_page_url":"https://zenodo.org/record/1495070","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/other"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/1495070","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008481817","display_name":"William N. Havard","orcid":"https://orcid.org/0000-0002-1226-4156"},"institutions":[{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210160287","display_name":"Laboratoire de Linguistique et Didactique des Langues Etrang\u00e8res et Maternelles","ror":"https://ror.org/05588ks88","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210139971","https://openalex.org/I4210150872","https://openalex.org/I4210160287","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Havard, William N.","raw_affiliation_strings":["Universit\u00e9 Grenoble Alpes, LIG/GETALP and LIDILEM"],"raw_orcid":"https://orcid.org/0000-0002-1226-4156","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Grenoble Alpes, LIG/GETALP and LIDILEM","institution_ids":["https://openalex.org/I899635006","https://openalex.org/I4210104430","https://openalex.org/I4210160287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087788538","display_name":"Jean\u2010Pierre Chevrot","orcid":"https://orcid.org/0000-0003-0883-9321"},"institutions":[{"id":"https://openalex.org/I4210160287","display_name":"Laboratoire de Linguistique et Didactique des Langues Etrang\u00e8res et Maternelles","ror":"https://ror.org/05588ks88","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210139971","https://openalex.org/I4210150872","https://openalex.org/I4210160287","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Chevrot, Jean-Pierre","raw_affiliation_strings":["Universit\u00e9 Grenoble Alpes, LIDILEM"],"raw_orcid":"https://orcid.org/0000-0003-0883-9321","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Grenoble Alpes, LIDILEM","institution_ids":["https://openalex.org/I4210160287","https://openalex.org/I899635006"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040820339","display_name":"Laurent Besacier","orcid":"https://orcid.org/0000-0001-7411-9125"},"institutions":[{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Besacier, Laurent","raw_affiliation_strings":["Universit\u00e9 Grenoble Alpes, LIG/GETALP"],"raw_orcid":"https://orcid.org/0000-0001-7411-9125","affiliations":[{"raw_affiliation_string":"Universit\u00e9 Grenoble Alpes, LIG/GETALP","institution_ids":["https://openalex.org/I899635006","https://openalex.org/I4210104430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9452000260353088,"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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9452000260353088,"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/computer-science","display_name":"Computer science","score":0.5154641270637512},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3907405436038971},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.3402166962623596},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32992470264434814},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2117260992527008},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.04846036434173584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5154641270637512},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3907405436038971},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.3402166962623596},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32992470264434814},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2117260992527008},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.04846036434173584}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:1495070","is_oa":true,"landing_page_url":"https://zenodo.org/record/1495070","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.1495070","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.1495070","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:1495070","is_oa":true,"landing_page_url":"https://zenodo.org/record/1495070","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"This":[0,39],"dataset":[1,22,34,40,130,165],"consists":[2],"of":[3,31,78,140,227,257,268,276,322,333,348,359],"synthetically":[4],"spoken":[5],"captions":[6,229,250,259,279,314,324,340,350],"for":[7,28,43,177],"the":[8,12,32,132,144,149,163,193,201,228,252,258,261,269,278,281,286,290,294,304,316,323,326,334,342,349,352,360],"STAIR":[9,33,145,295],"dataset.":[10,146],"Following":[11],"same":[13],"methodology":[14],"as":[15],"Chrupa\u0142a":[16],"<em>et":[17],"al.</em>":[18],"(see":[19,48,166],"article":[20,49],"|":[21,23],"code)":[24],"we":[25],"generated":[26],"speech":[27,46,112,122],"each":[29,141,178,211,233],"caption":[30,142,192,291],"using":[35,183],"Google's":[36],"Text-to-Speech":[37],"API.":[38],"was":[41],"used":[42],"visually":[44],"grounded":[45,111],"experiments":[47],"accepted":[50],"at":[51],"ICASSP2019).":[52],"<pre><code>@INPROCEEDINGS{8683069,":[53],"author={W.":[54],"N.":[55],"{Havard}":[56],"and":[57,60,73,92,156,204],"J.":[58],"{Chevrot}":[59],"L.":[61],"{Besacier}},":[62],"booktitle={ICASSP":[63],"2019":[64,66],"-":[65],"IEEE":[67],"International":[68],"Conference":[69],"on":[70,90],"Acoustics,":[71],"Speech":[72,81],"Signal":[74,82],"Processing":[75],"(ICASSP)},":[76],"title={Models":[77],"Visually":[79],"Grounded":[80],"Pay":[83],"Attention":[84],"to":[85,159,190,210,232,289,298,308],"Nouns:":[86],"A":[87],"Bilingual":[88],"Experiment":[89],"English":[91],"Japanese},":[93],"year={2019},":[94],"volume={},":[95],"number={},":[96],"pages={8618-8622},":[97],"keywords={information":[98],"retrieval;natural":[99],"language":[100,119],"processing;neural":[101],"nets;speech":[102],"processing;word":[103],"processing;artificial":[104],"neural":[105,124],"attention;human":[106],"attention;monolingual":[107],"models;part-of-speech":[108],"tags;nouns;neural":[109],"models;visually":[110],"signal;English":[113],"language;Japanese":[114],"language;word":[115],"endings;cross-lingual":[116],"speech-to-speech":[117],"retrieval;grounded":[118],"learning;attention":[120],"mechanism;cross-lingual":[121],"retrieval;recurrent":[123],"networks.},":[125],"doi={10.1109/ICASSP.2019.8683069},":[126],"ISSN={2379-190X},":[127],"month={May},}</code></pre>":[128],"The":[129],"comprises":[131],"following":[133,150],"files":[134,139,202],":":[135,171,207],"<strong>mp3-stair.tar.gz</strong>":[136],":<strong>":[137],"</strong>MP3":[138],"in":[143,162,218,240,260,280,293,325,351],"Filenames":[147],"have":[148],"pattern":[151],"<em>imageID_captionID</em>,":[152],"where":[153,285],"both":[154],"<em>imageID</em>":[155],"<em>captionID":[157],"</em>correspond":[158],"those":[160],"provided":[161],"original":[164],"annotation":[167],"format":[168],"here)":[169],"<strong>dataset.mfcc.npy</strong>":[170],"Numpy":[172,219,241],"array":[173],"with":[174,185],"MFCC":[175,180,194,212,234],"vectors":[176,195],"caption.":[179],"were":[181],"extracted":[182],"python_speech_features":[184],"default":[186],"configuration.":[187],"To":[188],"know":[189],"which":[191],"belong":[196],"to,":[197],"you":[198],"can":[199],"use":[200],"dataset.words.txt":[203],"dataset.ids.txt.":[205],"<strong>dataset.words.txt</strong>":[206],"Captions":[208],"corresponding":[209,231],"vector":[213,235],"(line":[214,236],"number":[215,237],"=":[216,238],"position":[217,239],"array,":[220,242],"starting":[221,243],"from":[222,244],"0)":[223,245],"<strong>dataset.ids.txt":[224],"</strong>:":[225,249,265,273,313,320,330,339,346,356],"IDs":[226,256,321,347],"(<em>imageID_captionID</em>)":[230],"Splits":[246],"test":[247,253,262,270,282],"<strong>test.txt":[248],"comprising":[251,315,341],"split":[254,263,271,318,328,336,344,354,362],"<strong>test_ids.txt</strong>:":[255],"<strong>test_tagged.txt":[264],"tagged":[266,331,357],"version":[267,332,358],"<strong>test-alignments.json.zip":[272],"Forced":[274],"alignments":[275],"all":[277],"split.":[283],"(dictionary":[284],"key":[287],"corresponds":[288],"ID":[292],"dataset).":[296],"<em>Due":[297],"an":[299],"unknown":[300],"error":[301],"during":[302],"upload,":[303],"JSON":[305],"file":[306],"had":[307],"be":[309],"zipped...</em>":[310],"train":[311,317,327,335],"<strong>train.txt":[312],"<strong>train_ids.txt":[319],"<strong>train_tagged.txt":[329],"val":[337,343,353,361],"<strong>val.txt":[338],"<strong>val_ids.txt":[345],"<strong>val_tagged.txt":[355]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}