Subspace based Speech Enhancement using Common Vector Approach

In this paper, we propose a new speech enhancement method using the common vector approach. Common vector approach is a subspace method used in recognition applications. In the proposed method, we separate the noisy speech data into magnitude and phase in frequency domain. And also magnitude data is separated into common and difference parts using common vector. It is considered that difference part contains the noise. Therefore, this part is cleaned using Linear Minimum Mean Square Error Estimation. After this process, the magnitude data is reconstructed by combining common part. The frequency domain speech data is rebuilt by sum of the reconstructed magnitude data and keeped phase data and transform to time domain on each frame. The proposed method was evaluated under various noise conditions. The results are compared with several methods in well-known quality measures.