2021
DOI: 10.3390/app11157149
|View full text |Cite
|
Sign up to set email alerts
|

Experimental Evaluation of Deep Learning Methods for an Intelligent Pathological Voice Detection System Using the Saarbruecken Voice Database

Abstract: This work is focused on deep learning methods, such as feedforward neural network (FNN) and convolutional neural network (CNN), for pathological voice detection using mel-frequency cepstral coefficients (MFCCs), linear prediction cepstrum coefficients (LPCCs), and higher-order statistics (HOSs) parameters. In total, 518 voice data samples were obtained from the publicly available Saarbruecken voice database (SVD), comprising recordings of 259 healthy and 259 pathological women and men, respectively, and using … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
11
0
1

Year Published

2022
2022
2025
2025

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 25 publications
(12 citation statements)
references
References 33 publications
0
11
0
1
Order By: Relevance
“…This research was also compared to other studies that used the same workflow ( Table 7 ). The key benefit of this study is that it produced better accuracy using the vowel /a/ than prior studies that employed all of the vowels to train the model [ 57 ]. With the LPCCs parameter in the /u/ vowel in men, the CNN classifier attained the best accuracy, 82.69%.…”
Section: Resultsmentioning
confidence: 99%
“…This research was also compared to other studies that used the same workflow ( Table 7 ). The key benefit of this study is that it produced better accuracy using the vowel /a/ than prior studies that employed all of the vowels to train the model [ 57 ]. With the LPCCs parameter in the /u/ vowel in men, the CNN classifier attained the best accuracy, 82.69%.…”
Section: Resultsmentioning
confidence: 99%
“…Voice data used in this project was accessed from the Saarbruecken voice database (SVD) hosted by Saarland University 21 . This database contains labeled healthy and pathological audio samples consisting of both sustained vowels (/a/, /i/, and /u/) and sentences 22,23 . The vowel samples were recorded in three different pitches: low, neutral, and high.…”
Section: Methodsmentioning
confidence: 99%
“…AI and related deep learning technologies have been shown to accelerate the time course and improve the quality of disease diagnosis and treatment monitoring. [13,14] Recently, advanced AI methods have been adopted for classifying airway-related symptoms such as cough [15,16] and deviated voice quality [17] in various clinical populations. Lean models have been proposed for the detection of cough in patients suffering from chronic cough, COPD, asthma, and lung cancer.…”
Section: Introductionmentioning
confidence: 99%