Spectral enhancement based on global soft decision

In this letter, we propose a novel speech enhancement technique based on gl obal soft decision. The proposed approach provides a unified framework for such procedures as speech absence probability (SAP) computation, spectral g ain modification, and noise spectrum estimation using the same statistical model assumption. Performances of the proposed enhancement algorithm are ev aluated by subjective tests under various environments and show better resu lts compared with the IS-127 standard enhancement method.