arXiv:1910.05453cs.CL
vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
HN submission. Found in a submission link or body. Submitters do not count as commenters in the main ranking; a submission is not an endorsement.
Abstract
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 the direct application of algorithms from the NLP community which require discrete inputs. Experiments show that BERT pre-training achieves a new state of the art on TIMIT phoneme classification and WSJ speech recognition.