Hardware implementation of MFCC feature extraction for respiratory sounds analysis

In this paper, an acoustic feature extraction method based on mel frequency cepstral coefficients (MFCC) was implemented on FPGA for real-time respiratory sound analysis. The proposed technique was implemented using Xilinx System Generator (XSG) in MATLAB/SIMULINK environment. The feature vectors obtained with fixed-point XSG implementation is compared to those obtained with on the floating-point MATLAB one using normal and wheezing respiratory sounds.