4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Recent Advances in Hypernasal Speech Detection using the Nonlinear Teager Energy Operator

Douglas A. Cairns, John H. L. Hansen, James F. Kaiser

Robust Speech Processing Laboratory, Department of Electrical Engineering, Duke University, Durham, NC, USA

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 significant difference between the Teager Energy profile for lowpass and bandpass filtered nasalized speech is shown, which is nonexistent for normal speech. An optimum classification algorithm is formulated that detects the presence of hypernasality using a measure of the difference in the Teager Energy profiles. The classification 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 classification algorithm.

Full Paper

Bibliographic reference.  Cairns, Douglas A. / Hansen, John H. L. / Kaiser, James F. (1996): "Recent advances in hypernasal speech detection using the nonlinear teager energy operator", In ICSLP-1996, 780-783.