Login / Signup

Pair Expansion for Learning Multilingual Semantic Embeddings Using Disjoint Visually-Grounded Speech Audio Datasets.

Yasunori OhishiAkisato KimuraTakahito KawanishiKunio KashinoDavid HarwathJames R. Glass
Published in: INTERSPEECH (2020)
Keyphrases
  • pairwise
  • learning algorithm
  • online learning
  • speech recognition
  • multimedia
  • learning process
  • active learning
  • digital audio
  • reinforcement learning
  • high level
  • audio visual
  • language acquisition
  • speech processing