Dominant distortion classification for pre-processing of vowels in remote biomedical voice analysis


Advances in speech signal analysis facilitate the development of techniques for remote biomedical voice assessment. However, the performance of these techniques is affected by noise and distortion in signals. In this paper, we focus on the vowel /a/ as the most widely-used voice signal for pathological voice assessments and investigate the impact of four major types of distortion that are commonly present during recording or transmission in voice analysis, namely: background noise, reverberation, clipping and compression, on Mel-frequency cepstral coefficients (MFCCs) - the most widely-used features in biomedical voice analysis. Then, we propose a new distortion classification approach to detect the most dominant distortion in such voice signals. The proposed method involves MFCCs as frame-level features and a support vector machine as classifier to detect the presence and type of distortion in frames of a given voice signal. Experimental results obtained from the healthy and Parkinson's voices show the effectiveness of the proposed approach in distortion detection and classification.

Publication DOI:
Divisions: College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: Copyright © 2017 ISCA
Event Title: 18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017
Event Type: Other
Event Dates: 2017-08-20 - 2017-08-24
Uncontrolled Keywords: Distortion analysis,MFCC,Remote biomedical voice assessment,Support vector machine,Language and Linguistics,Human-Computer Interaction,Signal Processing,Software,Modelling and Simulation
Last Modified: 16 Apr 2024 07:41
Date Deposited: 29 Mar 2018 09:45
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
PURE Output Type: Conference contribution
Published Date: 2017-08-24
Published Online Date: 2017-08-24
Accepted Date: 2017-08-24
Authors: Poorjam, Amir Hossein
Jensen, Jesper Rindom
Little, Max A. (ORCID Profile 0000-0002-1507-3822)
Christensen, Mads Græsbøll



Version: Accepted Version

| Preview

Export / Share Citation


Additional statistics for this record