SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set

Résumé

This paper presents an augmentation of MSCOCO dataset where speech is added to image and text. Speech captions are generated using text-to-speech (TTS) synthesis resulting in 616,767 spoken captions (more than 600h) paired with images. Disfluencies and speed perturbation are 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. Investigating multimodal learning schemes for unsupervised speech pattern discovery is also possible with this corpus, as demonstrated by a preliminary study conducted on a subset of the corpus (10h, 10k spoken captions).
Fichier principal
Vignette du fichier
GLU2017.pdf (2.28 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01580879 , version 1 (03-09-2017)

Identifiants

  • HAL Id : hal-01580879 , version 1

Citer

William N Havard, Laurent Besacier, Olivier Rosec. SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set. Grounding Language Understanding GLU2017 Workshop (Satellite of Interspeech 2017), Aug 2017, Stockholm, Sweden. ⟨hal-01580879⟩
183 Consultations
116 Téléchargements

Partager

Gmail Facebook X LinkedIn More