Enhancing Unsupervised Speech Recognition with Diffusion GANs
Computation and Language
2023-03-27 v1 Machine Learning
Sound
Audio and Speech Processing
Abstract
We enhance the vanilla adversarial training method for unsupervised Automatic Speech Recognition (ASR) by a diffusion-GAN. Our model (1) injects instance noises of various intensities to the generator's output and unlabeled reference text which are sampled from pretrained phoneme language models with a length constraint, (2) asks diffusion timestep-dependent discriminators to separate them, and (3) back-propagates the gradients to update the generator. Word/phoneme error rate comparisons with wav2vec-U under Librispeech (3.1% for test-clean and 5.6% for test-other), TIMIT and MLS datasets, show that our enhancement strategies work effectively.
Cite
@article{arxiv.2303.13559,
title = {Enhancing Unsupervised Speech Recognition with Diffusion GANs},
author = {Xianchao Wu},
journal= {arXiv preprint arXiv:2303.13559},
year = {2023}
}
Comments
5 pages, 1 figure, accepted by ICASSP 2023