Time-frequency analysis of speech signal using Chirplet transform for automatic diagnosis of Parkinson’s disease

Warule, Pankaj; Mishra, Siba Prasad; Deb, Suman

doi:10.1007/s13534-023-00283-x

Cited by 10 publications

(2 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Acoustic phonation studies provide relevant speaker information that can be used to detect diseases such as Alzheimer's dementia, Parkinson's, and amyotrophic lateral sclerosis, among others, based on the biomechanical uniqueness of each individual. Such uniqueness is evident in the EWA-DB dataset, which focuses on Slovak speakers with Alzheimer's and Parkinson's diseases (Rusko et al, 2023), and a dataset that focuses on Spanish native speakers with Parkinson's disease (Orozco-Arroyave et al, 2014), as well as recent acoustic studies on Alzheimer's (Cai et al, 2023;Zolnoori et al, 2023) and Parkinson's (Warule et al, 2023) diseases. In the 2021 study by Lee (2021), two types of neural network models were developed for dysphonia detection: a Feedforward Neural Network (FNN) and a Convolutional Neural Network (CNN).…”

Section: Introductionmentioning

confidence: 99%

Identification of Smith–Magenis syndrome cases through an experimental evaluation of machine learning methods

Fernández-Ruiz,

Núñez-Vidal,

Hidalgo-delaguía

et al. 2024

Front. Comput. Neurosci.

View full text Add to dashboard Cite

This research work introduces a novel, nonintrusive method for the automatic identification of Smith–Magenis syndrome, traditionally studied through genetic markers. The method utilizes cepstral peak prominence and various machine learning techniques, relying on a single metric computed by the research group. The performance of these techniques is evaluated across two case studies, each employing a unique data preprocessing approach. A proprietary data “windowing” technique is also developed to derive a more representative dataset. To address class imbalance in the dataset, the synthetic minority oversampling technique (SMOTE) is applied for data augmentation. The application of these preprocessing techniques has yielded promising results from a limited initial dataset. The study concludes that the k-nearest neighbors and linear discriminant analysis perform best, and that cepstral peak prominence is a promising measure for identifying Smith–Magenis syndrome.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of Smith–Magenis syndrome cases through an experimental evaluation of machine learning methods

Fernández-Ruiz,

Núñez-Vidal,

Hidalgo-delaguía

et al. 2024

Front. Comput. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Voice features extracted from sustained vowels have been evaluated as potential parameters for both the diagnosis and monitoring of PD in several studies [8]- [15]. These features cover various aspects, including issues related to glottal vibration, the harmonics-to-noise ratio (HNR), the control of glottal pressure through the respiratory mechanism, and vocal tract control [16].…”

Section: Introductionmentioning

confidence: 99%

Voice-Based SVM Model Reliability for Identifying Parkinson’s Disease

Pah,

Indrawati,

Kumar

2023

IEEE Access

View full text Add to dashboard Cite

One of the possibilities for developing non-invasive computerized diagnostic tools for Parkinson's disease (PD) is to detect changes in the voice, known as Parkinsonian dysarthria. Numerous classification models have been developed to diagnose PD based on voice features. However, the performance of models developed and trained only using voice features extracted from people with PD and healthy people might be affected when tested on individuals with other voice-related pathological conditions. Therefore, we investigated the reliability of voice-based machine-learning models that were developed only using datasets of people with PD and healthy people for accurately identifying people without PD when they have other voice-related pathological conditions (i.e. dysphonia and laryngitis). Three different support vector machines (SVMs) were developed and tested on voice features extracted from healthy people and those with PD, dysphonia, and laryngitis. The results confirmed that a voice-based SVM classifier only trained on the dataset of people with PD and healthy people was equally reliable in classifying other voice-related pathological conditions, such as dysphonia and laryngitis, as non-PD cases.

show abstract

A hybrid approach to detecting Parkinson's disease using spectrogram and deep learning CNN-LSTM network

Shibina,

Thasleema

2024

Int J Speech Technol

View full text Add to dashboard Cite

Time-frequency analysis of speech signal using Chirplet transform for automatic diagnosis of Parkinson’s disease

Cited by 10 publications

References 45 publications

Identification of Smith–Magenis syndrome cases through an experimental evaluation of machine learning methods

Identification of Smith–Magenis syndrome cases through an experimental evaluation of machine learning methods

Voice-Based SVM Model Reliability for Identifying Parkinson’s Disease

A hybrid approach to detecting Parkinson's disease using spectrogram and deep learning CNN-LSTM network

Contact Info

Product

Resources

About