Knowledge Commons of Institute of Automation,CAS
Adversarial Multilingual Training for Low-Resource Speech Recognition | |
Jiangyan Yi; Jianhua Tao; Zhengqi Wen; Ye Bai | |
2018 | |
会议名称 | 43th IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP 2018) |
会议日期 | 2018.04.15-2018.04.20 |
会议地点 | Calgary, AB, Canada |
摘要 | This paper proposes an adversarial multilingual training to train bottleneck (BN) networks for the target language. A parallel shared-exclusive model is also proposed to train the BN network. Adversarial training is used to ensure that the shared layers can learn language-invariant features. Experiments are conducted on IARPA Babel datasets. The results show that the proposed adversarial multilingual BN model outperforms the baseline BN model by up to 8.9% relative word error rate (WER) reduction. The results also show that the proposed parallel shared-exclusive model achieves up to 1.7% relative WER reduction when compared with the stacked share-exclusive model. |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40665 |
专题 | 多模态人工智能系统全国重点实验室_智能交互 |
作者单位 | 1.中国科学院自动化研究所; 2.中国科学院大学 |
推荐引用方式 GB/T 7714 | Jiangyan Yi,Jianhua Tao,Zhengqi Wen,et al. Adversarial Multilingual Training for Low-Resource Speech Recognition[C],2018. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
5会议-Adversarial Mult(1343KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论