Utterance-level Permutation Invariant Training with Discriminative Learning for Single Channel Speech Separation | |
Fan, Cunhang1,2; Liu, Bin1; Tao, Jianhua1,2,3; Wen, Zhengqi1; Yi, Jiangyan1; Bai, Ye1,2 | |
2018-11 | |
会议日期 | 26-29 Nov. 2018 |
会议地点 | Taipei, Taiwan |
英文摘要 | The challenge in deep learning for speaker independent speech separation comes from the label ambiguity or permutation problem. Utterance-level permutation invariant training (uPIT) technique solves this problem by minimizing the mean square error (MSE) over all permutations between outputs and targets. It is a state-of-the-art deep learning architecture. However, uPIT only minimizes the chosen permutation with the lowest MSE, not discriminates it with other permutations. This may lead to increase the possibility of remixing the separated sources. In this paper, we propose a uPIT with discriminative learning (uPITDL) method to solve this problem by adding one regularization at the cost function. In other words, we minimize the difference between the outputs of model and their corresponding reference signals. Moreover, the dissimilarity between the prediction and the targets of other sources is maximized. We evaluate the proposed model on WSJ0-2mix dataset. Experimental results show 22.0% and 24.8% relative improvements under both closed and open conditions compared with the uPIT baseline. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44392] |
专题 | 模式识别国家重点实验室_智能交互 |
通讯作者 | Tao, Jianhua |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology |
推荐引用方式 GB/T 7714 | Fan, Cunhang,Liu, Bin,Tao, Jianhua,et al. Utterance-level Permutation Invariant Training with Discriminative Learning for Single Channel Speech Separation[C]. 见:. Taipei, Taiwan. 26-29 Nov. 2018. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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