Open AccessUsing the Fisher Vector Approach for Cold Identification
Author(s) -
José Vicente Egas-López,
Gábor Gosztolya
Publication year - 2021
Publication title -
acta cybernetica
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.143
H-Index - 18
eISSN - 2676-993X
pISSN - 0324-721X
DOI - 10.14232/actacyb.287868
Subject(s) - computer science , normalization (sociology) , support vector machine , pattern recognition (psychology) , speech recognition , artificial intelligence , discriminative model , mel frequency cepstrum , principal component analysis , mixture model , fisher kernel , machine learning , feature extraction , kernel method , kernel fisher discriminant analysis , sociology , anthropology
In this paper, we present a computational paralinguistic method for assessing whether a person has an upper respiratory tract infection (i.e. cold) using their speech. Having a system that can accurately assess a cold can be helpful for predicting its propagation. For this purpose, we utilize Mel-frequency Cepstral Coefficients (MFCC) as audio-signal representations, extracted from the utterances, which allowed us to fit a generative Gaussian Mixture Model (GMM) that serves to produce an encoding based on the Fisher Vector (FV) approach. Here, we use the URTIC dataset provided by the organizers of the ComParE Challenge 2017 of the Interspeech Conference. The classification is done by a linear kernel Support Vector Machines (SVM); owing to the high imbalance of classes on the training dataset, we opt for undersampling the majority class, that is, to reduce the number of samples to those of the minority class. We find that applying Power Normalization (PN) and Principal Component Analysis (PCA) on the Fisher vector features is an effective strategy for the classification performance. We get better performance than that of the Bag-of-Audio-Words approach reported in the paper of the challenge.