Published October 24, 2020 | Version v1
Conference paper Open

Show and Speak: Directly Synthesize Spoken Description of Images

Authors/Creators

  • 1. Xi'an Jiaotong University
  • 2. Delft University of Technology
  • 3. University of Illinois at Urbana-Champaign

Description

This database is for the image-to-speech task. (Flickr8k)

Files

Files (11.7 GB)

Name Size
md5:cf5eb29062cd91893e4c096a9d79c8e4
11.7 GB Download