Non-intrusive speech quality assessment using deep belief network and backpropagation neural network

In this paper, we present a new speech quality assessment method to estimate the quality of degraded speech without the reference speech. The traditional non-intrusive assessment methods cannot meet the requirement of high consistency with subjective results owing to the lack of original reference signals. To solve these issues, deep belief network is trained to produce pseudo-reference speech signal of degraded speech. Then mel-frequency cepstrum coefficients of pseudo-reference speech and degraded speech are extracted to calculate feature differences. The feature differences are mapped to speech quality score using backpropagation neural network. Experiments are conducted in a dataset containing various degraded speech signals and subjective listening scores. When compared with the standardization ITU-T P.563, Gaussian Mixture Model method and the autoencoder-based method, the proposed method brings about a higher correlation coefficient between predicted scores and subjective scores.