子空间算法是一种基于矩阵特征空间分解的方法，信号子空间由阵列接收到的数据协方差矩阵中与信号对应的特征向量组成噪声子空间则由协方差矩阵中所有最小特征值噪声方差对应的特征向量组成。子空间算法就是利用这两个互补空间之间的正交特性来估计空间信号的方位-Subspace algorithms is minimized by the corresponding eigenvalues ​ ​ of all the noise variance-covariance matrix of a

PHT矩分解。用于音频或者图像数据的极谐波变换，使音频数据在受攻击后仍能够较好的提取水印-PHT matrix decomposition.Audio frequency or image data of Fourier transform, the audio data in attack can still good after extracting the watermark

本文提出了一种基于非负矩阵分解的方法来执行语音活动检测，其不需要来自用户的训练数据，并且对于中的变化是鲁棒的噪声环境。- This paper has presented a method based on non-negative matrix factorization for performing voice activity detection that requires no training data the user and is robust to changes in