点击次数：

论文类型：期刊论文

发表时间：2011-11-01

发表刊物：Journal of Convergence Information Technology

收录刊物：EI、Scopus

卷号：6

期号：11

页面范围：293-299

摘要：Forensic speech usually suffers from noise, distortion, interfering sounds, and other signal processing challenges that can impede proper analysis. The most common enhancement issue for forensic speech only could remove amplitude spectrum of background noise from the record. This paper proposes a new two-dimensional speech enhancement method which adopts parallel Wiener filter array in fractional Fourier transform domain to remove amplitude spectrum and phase spectrum of background noise. Theoretical analysis and experiments are conducted and the experiment shows that it has significantly superior Signal-to-Noise ratio over wiener filtering under the colored noise and white noise. It has wide application prospects in forensic speech recognition and speaker recognition.