TY - GEN
T1 - A Parametric Approach for Classification of Distortions in Pathological Voices
AU - Poorjam, Amir Hossein
AU - Little, Max A
AU - Jensen, Jesper Rindom
AU - Christensen, Mads Græsbøll
PY - 2018/9/10
Y1 - 2018/9/10
N2 - In biomedical acoustics, distortion in voice signals, commonly pre- sent during acquisition and transmission, adversely affects acoustic features extracted from pathological voice. Information on the type of distortion can help in compensating for its effects. This paper proposes a new approach to detecting four major types of commonly encountered distortion in remote analysis of pathological voice, na- mely background noise, reverberation, clipping and coding. In this approach, by applying factor analysis to Gaussian mixture model mean supervectors, distortions in variable-duration recordings are modeled by fixed-length, low-dimensional channel vectors. Then, linear discriminant analysis (LDA) is used to remove the remaining nuisance effects in the channel vectors. Finally, two different clas- sifiers, namely support vector machines and probabilistic LDA clas- sify the different types of distortion. Experimental results obtained using Parkinson’s voices, as an example of pathological voice, show 11.4% relative improvement in performance over systems which di- rectly use acoustic features for distortion classification.
AB - In biomedical acoustics, distortion in voice signals, commonly pre- sent during acquisition and transmission, adversely affects acoustic features extracted from pathological voice. Information on the type of distortion can help in compensating for its effects. This paper proposes a new approach to detecting four major types of commonly encountered distortion in remote analysis of pathological voice, na- mely background noise, reverberation, clipping and coding. In this approach, by applying factor analysis to Gaussian mixture model mean supervectors, distortions in variable-duration recordings are modeled by fixed-length, low-dimensional channel vectors. Then, linear discriminant analysis (LDA) is used to remove the remaining nuisance effects in the channel vectors. Finally, two different clas- sifiers, namely support vector machines and probabilistic LDA clas- sify the different types of distortion. Experimental results obtained using Parkinson’s voices, as an example of pathological voice, show 11.4% relative improvement in performance over systems which di- rectly use acoustic features for distortion classification.
KW - Channel factors
KW - Distortion modeling
KW - PLDA
KW - Remote pathological voice analysis
KW - SVM
UR - http://www.scopus.com/inward/record.url?scp=85054290541&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2018.8461316
DO - 10.1109/ICASSP.2018.8461316
M3 - Article in proceeding
SN - 978-1-5386-4659-5
T3 - I E E E International Conference on Acoustics, Speech and Signal Processing. Proceedings
SP - 286
EP - 290
BT - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PB - IEEE
T2 - 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Y2 - 15 April 2018 through 20 April 2018
ER -