Characteristics of multi-layer perceptron models in enhancing degraded speech

SUMMARY A multi-layer perceptron (MLP) acting directly in the time-domain is applied as a speech signal enhancer, and the performance examined in the context of three common classes of degradation, namely low bit-rate CELP degradation ie non-linear system degradation, additive noise, and convolution by a linear system. The investigation focuses on two topics: (i) the innuence of non-linearities within the network and (ii) network topology, comparing single and multiple output structures. The objective is to examine how these characteristics innuence network performance and whether this depends on the class of degradation. Experimental results show the importance of matching the en-hancer to the class of degradation. In the case of the CELP coder the standard MLP with its inherently non-linear characteristics is shown to be consistently better than any equivalent linear structure (up to 3.2 dB compared with 1.6 dB SNR improvement). In contrast, when the degradation is from additive noise, a linear enhancer is always superior.