vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations.

Alexei Baevski Steffen Schneider Michael Auli

Published in: ICLR (2020)

Keyphrases

reinforcement learning
vector quantization
learning tasks
learning process
multiscale
prior knowledge
mobile learning
speech signal
multiple representations
active learning
online learning
unsupervised learning
learning systems
learning problems
learning mechanism
spoken language