Self-supervised learning (SSL) models confront challenges of abrupt informational collapse or slow dimensional collapse. We propose TriNet, which introduces a novel triple-branch architecture for preventing collapse and stabilizing the pre-training. TriNet learns the SSL latent embedding space and incorporates it to a higher level space for predicting pseudo target vectors generated by a frozen teacher. Our experimental results show that the proposed method notably stabilizes and accelerates pre-training and achieves a relative word error rate reduction (WERR) of 6.06% compared to the state-of-the-art (SOTA) Data2vec for a downstream benchmark ASR task. We will release our code at https://github.com/tencent-ailab/.
@article{arxiv.2301.00656,
title = {TriNet: stabilizing self-supervised learning from complete or slow collapse on ASR},
author = {Lixin Cao and Jun Wang and Ben Yang and Dan Su and Dong Yu},
journal= {arXiv preprint arXiv:2301.00656},
year = {2023}
}