Steffen Schneider

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

2019 · ArXiv.org

We propose vq-wav2vec to learn discrete representations of audio segments through a wav2vec-style self-supervised context prediction task. The algorithm uses either a gumbel softmax or online k-means clustering to quantize the dense representations. Discretization enables …

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

2020 · arXiv (Cornell University)

We propose vq-wav2vec to learn discrete representations of audio segments through a wav2vec-style self-supervised context prediction task. The algorithm uses either a gumbel softmax or online k-means clustering to quantize the dense representations. Discretization enables …