A Register Array Based Low Power FFT Processor for Speech Recognition
Gin-Der Wu, Ying Lei · Journal of information science and engineering · 2008
Fast Fourier Transform (FFT) plays an important role in the field of digital signal processing. High performance FFT processors are widely used in different application, such as speech processing, image processing, and communication system. In this paper, we proposed a novel register array based low power FFT processor for Mel Frequency Cepstral Coefficient (MFCC). Compared with [9-12], this novel architecture can reduce more power consumption. This approach is very attractive for the speech feature extraction of MFCC.