Robust phoneme recognition using MLP neural networks in various domains of MFCC features

This paper focuses on enhancing MFCC features using a set of MLP NN in order to improve phoneme recognition accuracy under different noise types and SNRs. A NN can be used in different domains (between any pair of MFCC feature extraction blocks). It includes FFT, MEL, LOG, DCT and DELTA domains. Various domains have different complexities and achieve different degrees. A comparative study is done in this paper in order to find the best domain. Furthermore, a set of MLP NNs, instead of one NN, is used to enhance various noise types with different levels of SNRs. In this case, each NN is trained with a special noise type and SNR. The database used in the simulations is created by artificially adding different types of noises from the NOISEX-92 database to a subset of TIMIT speech corpus. Our experiments show that the highest improvement is achievable in LOG domain. It is also shown that although the performance decreases slightly in the DCT domain, the complexity is reduced to one fourth in this domain.