A Survey on Machine Learning Approaches for Automatic Detection of Voice Disorders

Hegde, Sarika; Shetty, Surendra; Rai, Smitha; Dodderi, Thejaswi

doi:10.1016/j.jvoice.2018.07.014

Cited by 125 publications

(69 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This observation is also in line with results reported in [13]. Table VI shows the results for the continuous speech sentences in the SVD database with individual feature sets (FS-1 to FS-7) and combination of feature sets (FS-8 to FS- It is worth noting that there exist studies in the literature [4], [67], [82] which report detection performance superior to that obtained in this study, but many of those studies have only included a small portion of the database and/or limited the analyses to a restricted number of pathologies. It is observed that the trend in the results reported in this paper are in line with the results reported in [13], [85].…”

Section: Pathology Detection Experimentssupporting

confidence: 89%

“…Regarding classifiers, several known techniques, such as kNN, GMM, LDA, HMM, ANN, CNN and SVM, have been used for pathological voice [25], [27], [40], [58]- [66]. Among the different classifiers, SVM has been found to be the most suitable classifier for voice pathology detection [67]. More details of various classifiers and machine learning techniques used for voice pathology detection can be found in the recent review published in [67].…”

Section: Introductionmentioning

confidence: 99%

“…Among the different classifiers, SVM has been found to be the most suitable classifier for voice pathology detection [67]. More details of various classifiers and machine learning techniques used for voice pathology detection can be found in the recent review published in [67].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis and Detection of Pathological Voice Using Glottal Source Features

Kadiri

Alku

2020

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

Automatic detection of voice pathology enables objective assessment and earlier intervention for the diagnosis. This study provides a systematic analysis of glottal source features and investigates their effectiveness in voice pathology detection. Glottal source features are extracted using glottal flows estimated with the quasi-closed phase (QCP) glottal inverse filtering method, using approximate glottal source signals computed with the zero frequency filtering (ZFF) method, and using acoustic voice signals directly. In addition, we propose to derive mel-frequency cepstral coefficients (MFCCs) from the glottal source waveforms computed by QCP and ZFF to effectively capture the variations in glottal source spectra of pathological voice. Experiments were carried out using two databases, the Hospital Universitario Príncipe de Asturias (HUPA) database and the Saarbrücken Voice Disorders (SVD) database. Analysis of features revealed that the glottal source contains information that discriminates normal and pathological voice. Pathology detection experiments were carried out using support vector machine (SVM). From the detection experiments it was observed that the performance achieved with the studied glottal source features is comparable or better than that of conventional MFCCs and perceptual linear prediction (PLP) features. The best detection performance was achieved when the glottal source features were combined with the conventional MFCCs and PLP features, which indicates the complementary nature of the features.

show abstract

Section: Pathology Detection Experimentssupporting

confidence: 89%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis and Detection of Pathological Voice Using Glottal Source Features

Kadiri

Alku

2020

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

show abstract

“…The main novelty of the study consists of the acquisition and analysis of voice samples collected through smartphones. Indeed, although a few studies have previously used smartphones to collect voice samples in patients with voice disorders [ 60 , 61 , 62 ], so far no authors have used this methodological approach to examine age-related changes of voice. The use of smartphones allows a simplified procedure of voice recordings and open to the acquisition of a large amount of data collected in an ecologic scenario.…”

Section: Discussionmentioning

confidence: 99%

Machine-Learning Analysis of Voice Samples Recorded through Smartphones: The Combined Effect of Ageing and Gender

Asci

Costantini

Leo

et al. 2020

Sensors

View full text Add to dashboard Cite

Background: Experimental studies using qualitative or quantitative analysis have demonstrated that the human voice progressively worsens with ageing. These studies, however, have mostly focused on specific voice features without examining their dynamic interaction. To examine the complexity of age-related changes in voice, more advanced techniques based on machine learning have been recently applied to voice recordings but only in a laboratory setting. We here recorded voice samples in a large sample of healthy subjects. To improve the ecological value of our analysis, we collected voice samples directly at home using smartphones. Methods: 138 younger adults (65 males and 73 females, age range: 15–30) and 123 older adults (47 males and 76 females, age range: 40–85) produced a sustained emission of a vowel and a sentence. The recorded voice samples underwent a machine learning analysis through a support vector machine algorithm. Results: The machine learning analysis of voice samples from both speech tasks discriminated between younger and older adults, and between males and females, with high statistical accuracy. Conclusions: By recording voice samples through smartphones in an ecological setting, we demonstrated the combined effect of age and gender on voice. Our machine learning analysis demonstrates the effect of ageing on voice.

show abstract

“…Selection of salient features from the whole features is needed to reduce the misclassification error rate [8]. Some of the popular techniques for dimensional reduction are GA, Principal Component Analysis, ReliefF, Linear Discriminant Analysis, Higher-Order Singular Value Decomposition, Fisher Discrimination Ratio and Minimum Redundancy Maximum Relevance [12]. According to Roffo [13], the overfitting chances increase with the number of features, therefore, feature selection can improve algorithms performance and classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Dual-Tree Complex Wavelet Packet Based Entropy Features for Voice Pathologies Detection

et al. 2020

View full text Add to dashboard Cite

The Dual-Tree Complex Wavelet Packet Transform (DT-CWPT) has been successfully implemented in numerous field because it introduces limited redundancy, provides approximately shift-invariance and geometrically oriented signal in multiple dimensions where these properties are lacking in traditional wavelet transform. This paper investigates the performance of features extracted using DT-CWPT algorithms which are quantified using k-Nearest Neighbors (k-NN) and Support Vector Machine (SVM) classifiers for detecting voice pathologies. Decomposition is done on the voice signals using Shannon and Approximate entropy (ApEn) to signify the complexity of voice signals in time and frequency domain. Feature selection methods using the ReliefF algorithm and Genetic algorithm (GA) are applied to obtain the optimum features for multiclass classification. It is observed that the best accuracies obtained using DT-CWPT with ApEn entropy are 91.15 % for k-NN and 93.90 % for SVM classifiers. The proposed work provides a promising detection rate for multiple voice disorders and is useful for the development of computer-based diagnostic tools for voice pathology screening in health care facilities.

show abstract

A Survey on Machine Learning Approaches for Automatic Detection of Voice Disorders

Cited by 125 publications

References 80 publications

Analysis and Detection of Pathological Voice Using Glottal Source Features

Analysis and Detection of Pathological Voice Using Glottal Source Features

Machine-Learning Analysis of Voice Samples Recorded through Smartphones: The Combined Effect of Ageing and Gender

Optimization of Dual-Tree Complex Wavelet Packet Based Entropy Features for Voice Pathologies Detection

Contact Info

Product

Resources

About