An Implementation of the Speech Recognition System based on USN
Kang Hyeon Rhee · ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications · 2007
The proposed system consists of a wireless audio sensor, a speech recognition algorithm using the psychoacoustic model, FFT (Fast Fourier Transform) and LDPC (Low Density Parity Check). The proposed speech recognition system is inserted in a HOST PC to use sensor energy effectively. To improve accuracy of speech recognition, a FEC (Forward Error Correction) system is also implemented. We optimized the simulation coefficient and the test environment to effectively remove wireless channel noises and to correct wireless channel errors.