Knowledge Commons of Institute of Automation,CAS
Improving Speech Separation with Adversarial Network and Reinforcement Learning | |
Liu, Guangcan1,2; Shi, Jing1,2,3![]() ![]() ![]() ![]() | |
2018-07 | |
会议名称 | 2018 International Joint Conference on Neural Networks (IJCNN) |
会议日期 | 2018-07 |
会议地点 | Rio de Janeiro, Brazil |
摘要 | In contrast to the conventional deep neural network for single-channel speech separation, we propose a separation framework based on adversarial network and reinforcement learning. The purpose of the adversarial network inspired by the generative adversarial network is to make the separated result and ground-truth with the same data distribution by evaluating the discrepancy between them. Meanwhile, in order to enable the model to bias the generation towards desirable metrics and reduce the discrepancy between training loss (such as mean squared error) and testing metric (such as SDR), we present the future success based on reinforcement learning. We directly optimize the performance metric to accomplish exactly that. With the combination of adversarial network and reinforcement learning, our model is able to improve the performance of single-channel speech separation. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48922 |
专题 | 复杂系统认知与决策实验室_听觉模型与认知计算 |
通讯作者 | Xu, Jiaming |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences (CASIA). Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.University of Chinese Academy of Sciences 4.Center for Excellence in Brain Science and Intelligence Technology, CAS. China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Liu, Guangcan,Shi, Jing,Chen, Xiuyi,et al. Improving Speech Separation with Adversarial Network and Reinforcement Learning[C],2018. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Improving Speech Sep(2787KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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