FPGA implementation of Real Time acoustic noise suppression by Spectral Subtraction using Dynamic Moving Average Method

The Paper presents the outlines of the field programmable gate array (FPGA) implementation of real time speech enhancement by spectral subtraction of acoustic noise using dynamic moving average method. It describes an stand alone algorithm for speech enhancement and presents a architecture for the implementation. The traditional spectral subtraction method can only suppress stationary acoustic noise from speech by subtracting the spectral noise bias calculated during non-speech activity, while adding the unique option of dynamic moving averaging to it, it can now periodically upgrade the estimation and cope up with changes in noise level. Signal to noise ratio (SNR) has been tested at different noisy environment and the improvement in SNR certifies the effectiveness of the algorithm. The FPGA implementation presented in this paper, works on streaming speech signals and can be used in factories, bus terminals, cellular phones, or in outdoor conferences where a large number of people have gathered. The Table in the experimental result section consolidates our claim of optimum resource usage.