Title: DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT
Authors: Heng-Jui Chang, Shu-wen Yang, Hung-yi Lee
Published: 5th October 2021 (Tuesday) @ 09:34:44
Link: http://arxiv.org/abs/2110.01900v4
Abstract
Self-supervised speech representation learning methods like wav2vec 2.0 and Hidden-unit BERT (HuBERT) leverage unlabeled speech data for pre-training and offer good representations for numerous speech processing tasks. Despite the success of these methods, they require large memory and high pre-training costs, making them inaccessible for researchers in academia and small companies. Therefore, this paper introduces DistilHuBERT, a novel multi-task learning framework to distill hidden representations from a HuBERT model directly. This method reduces HuBERTâs size by 75% and 73% faster while retaining most performance in ten different tasks. Moreover, DistilHuBERT required little training time and data, opening the possibilities of pre-training personal and on-device SSL models for speech.