Title: A consolidative evaluation of extracted EGG speech signal for pathology identification
Authors: Satyajit Pangaonkar; Reena Gunjan
Addresses: School of Engineering, Avantika University, Vishwanathpuram, Lekoda Village, Madhya Pradesh, India ' Department of Electronics and Communication Engineering, School of Engineering, MIT Art, Design and Technology University, Rajbaug, Loni-Kalbhor, Pune, India
Abstract: Speech as a natural and effective way of communication needs an appropriate analysis. This assessment is mainly used to quantify specific signals with various irregularities. The electroglottograph (EGG) helps to understand the functional utility of the exact state of the vocal fold in terms of vibration stage. But noise, gender dependencies and spectral measures limitations lead to inadequate description of vibratory state of the vocal fold. The proposed integrative approach of parametric evaluation uses software tools like Phonatory Dynamics (FonaDyn) which analyse the vibrational modes using clustering. Also, a Multi-dimensional Voice Program (MDVP) which estimates normative-based parametric statistics along with PRAAT (software for speech analysis in phonetics) and BioVoice (perceptual interpretation of speech signal) defines spectrographic relational stratagem. Interfacing FonaDyn, MDVP, and PRAAT and BioVoice with EGG experimentally identifies variability in the different parameters and enhances the graphical performance of the canonical grade statistical analysis for a phonatory gap pathology. The parametric accuracy of the diagnosis in terms of parameters will be effective for post processing of the speech analysis.
Keywords: electroglottograph; EGG; multi-dimensional voice program; MDVP; PRAAT; BioVoice; clustering; phonatory gap.
DOI: 10.1504/IJSPM.2021.118846
International Journal of Simulation and Process Modelling, 2021 Vol.16 No.4, pp.300 - 314
Received: 26 Oct 2020
Accepted: 05 Jun 2021
Published online: 08 Nov 2021 *