Transformer based unsupervised pre-training for acoustic representation learning
Abstract
Recently, a variety of acoustic tasks and related applications arised. For many acoustic tasks, the labeled data size may be limited. To handle this problem, we propose an unsupervised pre-training method using Transformer based encoder to learn a general and robust high-level representation for all acoustic tasks. Experiments have been conducted on three kinds of acoustic tasks: speech emotion recognition, sound event detection and speech translation. All the experiments have shown that pre-training using its own training data can significantly improve the performance. With a larger pre-training data combining MuST-C, Librispeech and ESC-US datasets, for speech emotion recognition, the UAR can further improve absolutely 4.3% on IEMOCAP dataset. For sound event detection, the F1 score can further improve absolutely 1.5% on DCASE2018 task5 development set and 2.1% on evaluation set. For speech translation, the BLEU score can further improve relatively 12.2% on En-De dataset and 8.4% on En-Fr dataset.
Cite
@article{arxiv.2007.14602,
title = {Transformer based unsupervised pre-training for acoustic representation learning},
author = {Ruixiong Zhang and Haiwei Wu and Wubo Li and Dongwei Jiang and Wei Zou and Xiangang Li},
journal= {arXiv preprint arXiv:2007.14602},
year = {2021}
}
Comments
Accepted by ICASSP 2021