Exploiting Spectro-temporal Structures Using NMF For DNN-based Supervised Speech Separation | |
Nie S(聂帅)2; Shan Liang2; Hao Li1; XueLiang Zhang1; ZhanLei Yang2; WenJu Liu2 | |
2016-03 | |
会议日期 | 2016-3-20~2016-3-25 |
会议地点 | Shanghai, China |
英文摘要 | The targets of speech separation, whether ideal masks or magnitude spectrograms of interest, have prominent spectro-temporal structures. These characteristics are very worthy to be exploited for speech separation, however, they are usually ignored in previous works. In this paper, we use nonnegative matrix factorization (NMF) to exploit the spectro-temporal structures of magnitude spectrograms. With nonnegative constrains, NMF can capture the basis spectra patterns of speech and noise. Then the learned basis spectra are integrated into a deep neural network (DNN) to reconstruct the magnitude spectrograms of speech and noise with their nonnegative linear combination. Using the reconstructed spectrograms, we further explore a discriminative training objective and a joint optimization framework for the proposed model. Systematic experiments show that the proposed model is competitive with the previous methods in monaural speech separation tasks. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/40646] |
专题 | 模式识别国家重点实验室_智能交互 |
通讯作者 | Nie S(聂帅) |
作者单位 | 1.内蒙古大学 2.中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Nie S,Shan Liang,Hao Li,et al. Exploiting Spectro-temporal Structures Using NMF For DNN-based Supervised Speech Separation[C]. 见:. Shanghai, China. 2016-3-20~2016-3-25. |
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