Real-time implementation of Maximum a Posteriori (MAP) based noise reductions using Leon 3 System on Chip

Abstract

Maximum a Posteriori (MAP) is an advance method to estimate noise for various audio noise reduction applications. MAP algorithm with variable speech distribution involves complex and intensive computation. Implementation in naïve method can't achieve real-time constraint. This paper proposed a method to optimize the MAP algorithm with variable speech distribution in software implementation for System on Chip (SoC). System utilizes Leon 3 microprocessor as main processing system. System is implemented in software hardware co-design to ensure flexibility and reduce computational time burden. Optimization has been done by replacing some arithmetic function with approximation function and by giving optimization option in the compiler. The simulation results show that the optimized MAP algorithm produces a linear result in SNR enhancement and faster computation time under time budget constraint.