Links Between Markov Models and Multilayer Perceptrons
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
We propose a speech recognition method based on the dynamical model of speech production. The model consists of an articulator and its control command sequences. The latter has linguistic information of speech and the former has the articulatory information which determines the transformation from linguistic intentions to speech signals. This separation allows our speech recognition model to be more controllable. It also provides new approaches to coarticulation modeling. The effectiveness of the proposed model was examined by speaker-dependent letter recognition experiments.