{"data":{"id":"10.18709/perscido.2017.06.ds80","type":"dois","attributes":{"doi":"10.18709/perscido.2017.06.ds80","prefix":"10.18709","suffix":"perscido.2017.06.ds80","identifiers":[],"alternateIdentifiers":[],"creators":[{"name":"Besacier, Laurent","nameType":"Personal","givenName":"Laurent","familyName":"Besacier","affiliation":[],"nameIdentifiers":[]}],"titles":[{"lang":"en","title":"SPEECH-COCO"}],"publisher":"PerSciDo","container":{},"publicationYear":2017,"subjects":[{"lang":"en","subject":"Computer Science"},{"lang":"en","subject":"Linguistics"},{"subject":"FOS: Languages and literature","schemeUri":"http://www.oecd.org/science/inno/38235147.pdf","subjectScheme":"Fields of Science and Technology (FOS)"},{"subject":"FOS: Languages and literature","subjectScheme":"Fields of Science and Technology (FOS)"}],"contributors":[],"dates":[{"date":"2017-06-28","dateType":"Submitted"},{"date":"2017-06-29","dateType":"Accepted"},{"date":"2017","dateType":"Issued"}],"language":"en","types":{"ris":"DATA","bibtex":"misc","citeproc":"dataset","schemaOrg":"Dataset","resourceType":"Dataset/Image Data","resourceTypeGeneral":"Dataset"},"relatedIdentifiers":[],"relatedItems":[],"sizes":["57 GB"],"formats":["wav","json","sql"],"version":"1.0","rightsList":[{"lang":"en","rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"lang":"en","description":"SPEECH-COCO is an augmentation of MS-COCO dataset where speech is added to image and text. Speech captions were generated using text-to-speech (TTS) synthesis resulting in 616,767 spoken captions (\u0026gt;600h) paired with images. Disfluencies and speed perturbation were added to the signal in order to sound more natural. Each speech signal (WAV) is paired with a JSON file containing exact timecode for each word/syllable/phoneme in the spoken caption. Such a corpus could be used for Language and Vision (LaVi) tasks including speech input or output instead of text.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"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","url":"https://perscido.univ-grenoble-alpes.fr/datasets/DS80","contentUrl":null,"metadataVersion":1,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":0,"created":"2017-07-11T08:41:11.000Z","registered":"2017-07-11T08:41:11.000Z","published":"2017","updated":"2020-11-10T16:20:05.000Z"},"relationships":{"client":{"data":{"id":"inist.persyval","type":"clients"}},"provider":{"data":{"id":"vcob","type":"providers"}},"media":{"data":{"id":"10.18709/perscido.2017.06.ds80","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[]}}}}