Speech recognition by combining pairwise discriminant time-delay neural networks and predictive LR-parser

A phoneme recognition method using pairwise discriminant time-delay neural networks (PD-TDNNs) and a continuous speech recognition method using the PD-TDNNs are proposed. It is shown that classification-type neural networks have poor robustness against the difference in speaking rates between training data and testing data. To improve the robustness, the authors developed a phoneme recognition method using PD-TDNNs. This method has high performance owing to its particular mechanism, that is a majority decision by multiple less sharp discrimination boundaries. They tested these methods on both consonant recognition and phrase recognition, and obtained higher recognition performance compared with a conventional method using a single TDNN