Discrimination of Homographs Distorted by a Lengthy Impulsive Noise

Article type: Research Article

Authors: Paulikas, Šarūnas | Navakauskas, Dalius

Affiliations: Department of Telecommunications Engineering, Electronics Faculty, Vilnius Gediminas Technical University, Naugarduko 41-210, 03227 Vilnius, Lithuania, e-mail: sarunas.paulikas@el.vtu.lt | Department of Electronic Systems, Electronics Faculty, Vilnius Gediminas Technical University, Naugarduko 41-422, 03227 Vilnius, Lithuania, e-mail: dalius.navakauskas@el.vtu.lt

Abstract: The paper addresses the problem of discrimination of homographs when a lengthy segment of an uttered word is missing. The considered discrimination procedure is done by recognizer that operates on cepstrum coefficients extracted from the speech signal. For restoration of the missing speech segment rather than use of the known speech signal, it has been proposed to calculate speech signal characteristics: the period of fundamental frequency and intensity. By experimentation it has been shown that the polynomial approximation of speech signal characteristics improves homograph discrimination results. An extra computational burden associated with the proposed method is not high because it involves recalculation of the already extracted Fourier coefficients.

Keywords: homograph discrimination, speech recognition, speech signal processing, speech signal characteristics, restoration, approximation

Journal: Informatica, vol. 17, no. 2, pp. 297-304, 2006