Experiments in dysarthric speech recognition using artificial neural networks

In this study, we investigated the use of artificial neural networks (ANNs) to recognize dysarthric speech. Two multilayer neural networks were developed, trained, and tested using isolated words spoken by a dysarthric speaker. One network had the fast Fourier transform (FFT) coefficients as inputs, while the other network had the formant frequencies as inputs. The effect of additional features in the input vector on the recognition rate was also observed. The recognition rate was evaluated against the intelligibility rating obtained by five human listeners and also against the recognition rate of the Introvoice commercial speech-recognition system. Preliminary results demonstrated the ability of the developed networks to successfully recognize dysarthric speech despite its large variability. These networks clearly outperformed both the human listeners and the Introvoice commercial system.