.png){kind=icon}
返回
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
.png){kind=icon}
OA
AI
DOI：10.1109/JSTSP.2022.3188113.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks. As speech signal contains multi-faceted information including speaker identity, paralinguistics, spoken content, etc., learning universal representations for all speech tasks is challenging. To tackle the problem, we propose a new pre-trained model, WavLM, to solve full-stack downstream speech tasks. WavLM jointly learns masked speech prediction and denoising in pre-training. By this means, WavLM does not only keep the speech content modeling capability by the masked speech prediction, but also improves the potential to non-ASR tasks by the speech denoising. In addition, WavLM employs gated relative position bias for the Transformer structure to better capture the sequence ordering of input speech. We also scale up the training dataset from 60 k hours to 94 k hours. WavLM Large achieves state-of-the-art performance on the SUPERB benchmark, and brings significant improvements for various speech processing tasks on their representative benchmarks.
Keyword:
Task analysis
Predictive models
Transformers
Data models
Speech recognition
Convolution
Benchmark testing
Self-supervised learning
speech pre-training
期刊
IF:
13.7
论文数:
1.9K
被引数:
1.1W
机构
引用论文
.png){kind=icon}
分享收藏
HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units休伯特: 通过隐藏单元的掩蔽预测进行自我监督的语音表示学习OAAI
OAAI分享收藏分享收藏
查看更多内容