Parkinson’s Disease Detection from Speech Using Single Frequency Filtering Cepstral Coefficients

Abstract

Parkinson's disease (PD) is a progressive deterioration of the human central nervous system. Detection of PD (discriminating patients with PD from healthy subjects) from speech is a useful approach due to its non-invasive nature. This study proposes to use novel cepstral coefficients derived from the single frequency filtering (SFF) method, called as single frequency filtering cepstral coefficients (SFFCCs) for the detection of PD. SFF has been shown to provide higher spectro-temporal resolution compared to the short-time Fourier transform. The current study uses the PC-GITA database, which consists of speech from speakers with PD and healthy controls (50 males, 50 females). Our proposed detection system is based on the i-vectors derived from SFFCCs using SVM as a classifier. In the detection of PD, better performance was achieved when the ivectors were computed from the proposed SFFCCs compared to the popular conventional MFCCs. Furthermore, we investigated the effect of temporal variations by deriving the shifted delta cepstral (SDC) coefficients using SFFCCs. These experiments revealed that the i-vectors derived from the proposed SF-FCCs+SDC features gave an absolute improvement of 9% compared to the i-vectors derived from the baseline MFCCs+SDC features, indicating the importance of temporal variations in the detection of PD.

Assessment of Acoustic Features and Machine Learning for Parkinson’s Detection

“…ough the SVM approach of Kadiri et al [22] shows 73.32% detection accuracy, which is close to our approach, but at the same time, the number of vocal features used is not clearly highlighted.…”

“…Therefore, the proposed collaborative features on Naïve Bayes is a practical approach to Parkinson's detection. At the final stage of analysis, the proposed collaborative features-based Parkinson's detection system has been compared with the current state-of-the-art function-based methods, viz., Avuçlu and Elen [ 18 ], Bourouhou et al [ 19 ], Zhang et al [ 20 ], Meghraoui et al [ 21 ], Kadiri et al [ 22 ], Polat and Nour [ 25 ], Xiong and Lu [ 26 ] and Mekyska et al [ 28 ]. Since our approach is based on a function-based approach, most of the methods taken for comparison belong to function-based approaches such as Naïve Bayes and Support Vector Machine (SVM).…”

“…Finally, an extensive discussion has been carried out regarding the shortcoming and future direction of the proposed Parkinson's detection model. [18] Naïve Bayes 22 70.26 Bourouhou et al [19] Naïve Bayes 26 65.00 Zhang et al [20] Naïve Bayes 22 69.24 Meghraoui et al [21] Bernoulli Naïve Bayes 3 62.50 Kadiri et al [22] Support Vector Machine -73.32 Polat and Nour [25] Linear Regression 45 77.50 Xiong and Lu [26] Naïve Bayes 8 72.00 Mekyska et al [28] Classification and regression trees 8 75.19 Collaborative PD (proposed) Naïve Bayes 7 78.97…”

“…A test on 28 samples comes across with a 62.5% detection accuracy on Bernoulli Naïve Bayes (BNB) with 0.375 Mean Squared Error (MSE). Kadiri et al [22] e authors used the dataset proposed by Sakar et al [24], and the dataset contains replicated speech information of 252 subjects resulting in 756 instances. Machine learning methods cannot be directly applied to these instances as each subject has three readings of the speech signal.…”

“…A test on 28 samples comes across with a 62.5% detection accuracy on Bernoulli Naïve Bayes (BNB) with 0.375 Mean Squared Error (MSE). Kadiri et al [ 22 ] proposed a method of Parkinson's disease detection using SVM on Single Frequency Filtering Cepstral Coefficients (SFFCC) and Shifted Delta Cepstral (SDC) features exacted from voice signals of Parkinson's and control subjects. The SFFCC + SDC features witnessed 9% of performance improvements as compared to traditional MFCC + SDC features.…”