Title :
Real time implementation of an adaptive filter for speech enhancement
Author :
Creighton, John ; Doraiswami, R.
Author_Institution :
Dept. of Electr. & Comput. Eng., New Brunswick Univ., Fredericton, NB, Canada
Abstract :
An adaptive linear prediction filter for speech enhancement is implemented in real time on a PC interfaced to an A/D and D/A converter board. A least means squares (LMS) algorithm is employed to update the filter weights where the learning factor is adaptively adjusted to provide faster convergence. The prediction horizon is chosen to be larger than the correlation length of the noise, thereby not restricting the noise to be white. The voice activity and noise segment of the speech waveform are detected by using the energy of the adaptive filter output. This is used to attenuate the noise-only portion. The proposed scheme is evaluated on number of speech samples.
Keywords :
adaptive filters; adaptive signal processing; convergence; correlation methods; least mean squares methods; linear predictive coding; noise; speech enhancement; A/D and D/A converter board interfaced PC; LMS algorithm; adaptive filter output energy; adaptive linear prediction filter; adaptively adjusted learning factor; convergence; filter weights; least means squares algorithm; noise correlation length; noise-only portion attenuation; prediction horizon; real time PC implementation; real time implementation; speech enhancement; speech samples; speech waveform noise segment; voice activity; Adaptive filters; Algorithm design and analysis; Computer interfaces; Finite impulse response filter; Iterative algorithms; Least squares approximation; Niobium; Nonlinear filters; Robustness; Speech enhancement;
Conference_Titel :
Electrical and Computer Engineering, 2004. Canadian Conference on
Print_ISBN :
0-7803-8253-6
DOI :
10.1109/CCECE.2004.1347681
