Knowledge Commons of Institute of Automation,CAS
Language-invariant Bottleneck Features from Adversarial End-to-end Acoustic Models for Low Resource Speech Recognition | |
Jiangyan Yi; Jianhua Tao; Ye Bai | |
2019 | |
会议名称 | 44th IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP 2019) |
会议日期 | 2019.05.12-2019.05.18 |
会议地点 | Brighton, UK |
出版者 | 允许多值(多值间使用英文分号分隔) |
摘要 | This paper proposes to learn language-invariant bottleneck features from an adversarial end-to-end acoustic model for low resource languages. The multilingual end-to-end model is trained with a connectionist temporal classification loss function. The model has shared and private layers. The shared layers are the hidden layers utilized to learn universal features for all the languages. The private layers are the language-dependent layers used to capture language-specific features. Attention based adversarial end-to-end language identification is used to capture enough language information. Furthermore, orthogonality constraints are used to make private and shared features dissimilar. Experiments are conducted on IARPA Babel datasets. The results show that the target model trained with the proposed language-invariant bottleneck features outperforms the target model trained with the conventional multilingual bottleneck features by up to 9.7% relative word error rate reduction. |
七大方向——子方向分类 | 语音识别与合成 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40662 |
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,Ye Bai. Language-invariant Bottleneck Features from Adversarial End-to-end Acoustic Models for Low Resource Speech Recognition[C]:允许多值(多值间使用英文分号分隔),2019. |
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 | ||
2会议-Language-invaria(295KB) | 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