Non-linear predictor for speech enhancement
Tuan-Ho Le, J.S. Mason · 1994
This paper addresses the application of non-linear prediction to speech enhancement, considering 3 common cases of speech degraded by distinctly non-linear system (CELP coder), the addition of (Gaussian) noise, and convolution by a linear system. A time-domain non-linear predictor, in the form of an MLP neural net structure, is applied as an enhancer and the performance examined in all three cases, with respect to the influences of non-linearity and net topologies. Experimental results show that, in the case of low bitrate CELP coder degradation, nets with multiple outputs give significant improvement over single-output structures. It is also clear that in this case, i.e. nonlinear degradation, the matching non-linear enhancer is consistently better than the equivalent linear structures. In contrast, when the degradation is from additive noise, the (matching) linear enhancer is superior. Again, the multiple output cases give the best results. There is less consistence in the case of ...