Incorporating linguistic features in a hybrid HMM/MLP speech recognizer


V. Abrash, M. Cohen, H. Franco and I. Arima, “Incorporating linguistic features in a hybrid HMM/MLP speech recognizer,” Proceedings of ICASSP ’94. IEEE International Conference on Acoustics, Speech and Signal Processing, 1994, pp. II/673-II/676 vol.2, doi: 10.1109/ICASSP.1994.389566.


We have developed a hybrid speech recognition system which uses a multilayer perceptron (MLP) to estimate the observation likelihoods associated with the states of a HMM. In this paper, we propose two schemes for incorporating distinctive speech features (sonorant, fricative, nasal, vocalic, and voiced) into the MLP component of our system. We show a small improvement in recognition performance on a 160-word speaker-independent continuous-speech Japanese conference room reservation database. Further experiments simulating an improved distinctive feature classifier indicate that this approach can potentially lead to substantial performance improvements.

Read more from SRI