Recent advances in hypernasal speech detection using the nonlinear teager energy operator

Speakers with a defective velopharyngeal mechanism produce speech with inappropriate nasal resonance. It is of clinical interest to detect hypernasality as it is indicative of an anatomical, neurological, or peripheral nervous system problem. While clinical techniques exist for detecting hypernasality, a preferred approach would be noninvasive to maximize patient comfort and naturalness of speaking. In this study, a noninvasive technique based on the Teager Energy operator is proposed. Employing a proposed model for normal and nasalized speech, a signi cant di erence between the Teager Energy pro le for lowpass and bandpass ltered nasalized speech is shown, which is nonexistent for normal speech. An optimum classi cation algorithm is formulated that detects the presence of hypernasality using a measure of the di erence in the Teager Energy pro les. The classi cation algorithm was evaluated using native English speakers producing front and mid vowels. Results show that the presence of hypernasality in speech can be reliably detected (94.7%) using the proposed classi cation algorithm.