当前位置: X-MOL 学术Signal Image Video Process. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Joint constraint algorithm based on deep neural network with dual outputs for single-channel speech separation
Signal, Image and Video Processing ( IF 2.0 ) Pub Date : 2020-04-12 , DOI: 10.1007/s11760-020-01676-6
Linhui Sun , Ge Zhu , Pingan Li

Single-channel speech separation (SCSS) plays an important role in speech processing. It is an underdetermined problem since several signals need to be recovered from one channel, which is more difficult to solve. To achieve SCSS more effectively, we propose a new cost function. What’s more, a joint constraint algorithm based on this function is used to separate mixed speech signals, which aims to separate two sources at the same time accurately. The joint constraint algorithm not only penalizes residual sum of square, but also exploits the joint relationship between the outputs to train the dual output DNN. In these joint constraints, the training accuracy of the separation model can be further increased. We evaluate the proposed algorithm performance on the GRID corpus. The experimental results show that the new algorithm can obtain better speech intelligibility compared to the basic cost function. In the aspects of source-to-distortion ratio , signal-to-interference ratio, source-to-artifact ratio and perceptual evaluation of speech quality, the novel approach can obtain better performance.

中文翻译:

基于双输出深度神经网络的单通道语音分离联合约束算法

单通道语音分离 (SCSS) 在语音处理中起着重要作用。这是一个未确定的问题,因为需要从一个通道中恢复多个信号,这更难解决。为了更有效地实现 SCSS,我们提出了一个新的成本函数。更重要的是,基于该函数的联合约束算法用于分离混合语音信号,旨在准确地同时分离两个源。联合约束算法不仅惩罚残差平方和,还利用输出之间的联合关系来训练双输出 DNN。在这些联合约束下,可以进一步提高分离模型的训练精度。我们在 GRID 语料库上评估了所提出的算法性能。实验结果表明,与基本代价函数相比,新算法可以获得更好的语音清晰度。在语音质量的源失真比、信号干扰比、源伪像比和感知评估方面,该新方法可以获得更好的性能。
更新日期:2020-04-12
down
wechat
bug