Voice Disorder Signal Classification Using M-Band Wavelets and Support Vector Machine

Saidi, Pouria; Almasganj, Farshad

doi:10.1007/s00034-014-9927-x

Cited by 21 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…been used as input data within the various ML algorithms. Some of these features include fundamental frequency (F0), perturbation measures (jitter and shimmer), the harmonics-to-noise ratio, [20][21][22][23] Mel frequency cepstrum coefficients, [24][25][26][27][28] wavelet sub-band features, [29][30][31][32] Multi Dimensional Voice Program parameters [33][34][35] and glottal flow estimation parameters. 14 36 37 Several ML algorithms have been explored, such as support vector machines, 34 37-39 deep neural networks (DNNs), 28 40-42 k-nearest neighbours 12 43 44 and others.…”

Section: Open Accessmentioning

confidence: 99%

Voice disorder recognition using machine learning: a scoping review protocol

Gupta,

Gunjawate,

Nguyen

et al. 2024

BMJ Open

View full text Add to dashboard Cite

IntroductionOver the past decade, several machine learning (ML) algorithms have been investigated to assess their efficacy in detecting voice disorders. Literature indicates that ML algorithms can detect voice disorders with high accuracy. This suggests that ML has the potential to assist clinicians in the analysis and treatment outcome evaluation of voice disorders. However, despite numerous research studies, none of the algorithms have been sufficiently reliable to be used in clinical settings. Through this review, we aim to identify critical issues that have inhibited the use of ML algorithms in clinical settings by identifying standard audio tasks, acoustic features, processing algorithms and environmental factors that affect the efficacy of those algorithms.MethodsWe will search the following databases: Web of Science, Scopus, Compendex, CINAHL, Medline, IEEE Explore and Embase. Our search strategy has been developed with the assistance of the university library staff to accommodate the different syntactical requirements. The literature search will include the period between 2013 and 2023, and will be confined to articles published in English. We will exclude editorials, ongoing studies and working papers. The selection, extraction and analysis of the search data will be conducted using the ‘Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for scoping reviews’ system. The same system will also be used for the synthesis of the results.Ethics and disseminationThis scoping review does not require ethics approval as the review solely consists of peer-reviewed publications. The findings will be presented in peer-reviewed publications related to voice pathology.

show abstract

Section: Open Accessmentioning

confidence: 99%

Voice disorder recognition using machine learning: a scoping review protocol

Gupta,

Gunjawate,

Nguyen

et al. 2024

BMJ Open

View full text Add to dashboard Cite

show abstract

“…A pesquisa bibliográfica realizada mostrou que poucos trabalhos tentam diferenciar nódulos vocais e edema de Reinke. A maioria diferencia um grupo saudável e outro patológico, onde nódulos e edema estão incluídos, como [9], [10]. Outros distinguem diferentes grupos patológicos mas, neste caso, nódulos e edema estão no mesmo grupo, como [11], [12].…”

Section: Introductionunclassified

Diferenciação entre Edema de Reinke e Nódulos Vocais através de Parâmetros Não-Lineares da Voz

Silva¹,

Alves²,

Bispo³

et al. 2021

Anais Do XXXIX Simpósio Brasileiro De Telecomunicações E Processamento De Sinais

View full text Add to dashboard Cite

Resumo-Este trabalho tem como objetivo diferenciar distúrbios vocais relacionados com nódulo vocal e edema de Reinke através de parâmetros não-lineares. Os parâmetros são obtidos da banda completa e, por meio da transformada wavelet, de sub-bandas de vogal sustentada. A wavelet que maximiza a capacidade discriminante individual dos parâmetros é buscada. Duas seleções dos parâmetros em sub-bandas são realizadas. Os parâmetros em banda completa e em sub-bandas, e os conjuntos selecionados são aplicados a vários classificadores com validação cruzada leave-one-out. Acurácias de classificação de até 86,2% são obtidas sem seleção de parâmetros enquanto acurácias até 100% são alcançadas com parâmetros selecionados.Palavras-Chave-Nódulo vocal, edema de Reinke, parâmetros não-lineares, wavelet, classificação.

show abstract

“…This work involved 57 normal and 173 pathological signals from Massachusetts Eye and Ear Infirmary (MEEI) voice disorders database whilst 24 normal and 24 pathological voices from MAPACI speech pathology database. Saidi and Almasganj [7] classified the normal or pathological voice using a five-band wavelet system employing a GA to determine the optimal wavelet parameters and shown good performance close to 100%. Different samples containing 57 normal and 653 pathological signals from MEEI database were used.…”

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

Voice Disorder Signal Classification Using M-Band Wavelets and Support Vector Machine

Cited by 21 publications

References 18 publications

Voice disorder recognition using machine learning: a scoping review protocol

Voice disorder recognition using machine learning: a scoping review protocol

Diferenciação entre Edema de Reinke e Nódulos Vocais através de Parâmetros Não-Lineares da Voz

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

Contact Info

Product

Resources

About