Convolutional Neural Networks for Pathological Voice Detection

Wu, Huiyi; Soraghan, John J.; Lowit, Anja; Caterina, Gaetano Di

doi:10.1109/embc.2018.8513222

Cited by 36 publications

(22 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, other studies have used continuous speech samples for analyses [6]. CNNs extract features automatically from the spectrogram of voice recordings for dysphonia diagnosis, and a larger amount of training data yields better results [32]. Therefore, the CNN used here may have extracted more features from these entire voice samples, thereby achieving better training results with our model.…”

Section: Comparison With Prior Workmentioning

confidence: 99%

Deep Learning Application for Vocal Fold Disease Prediction Through Voice Recognition: Preliminary Development Study

Hu¹,

Chang²,

Wang³

et al. 2021

J Med Internet Res

View full text Add to dashboard Cite

Background Dysphonia influences the quality of life by interfering with communication. However, a laryngoscopic examination is expensive and not readily accessible in primary care units. Experienced laryngologists are required to achieve an accurate diagnosis. Objective This study sought to detect various vocal fold diseases through pathological voice recognition using artificial intelligence. Methods We collected 189 normal voice samples and 552 samples of individuals with voice disorders, including vocal atrophy (n=224), unilateral vocal paralysis (n=50), organic vocal fold lesions (n=248), and adductor spasmodic dysphonia (n=30). The 741 samples were divided into 2 sets: 593 samples as the training set and 148 samples as the testing set. A convolutional neural network approach was applied to train the model, and findings were compared with those of human specialists. Results The convolutional neural network model achieved a sensitivity of 0.66, a specificity of 0.91, and an overall accuracy of 66.9% for distinguishing normal voice, vocal atrophy, unilateral vocal paralysis, organic vocal fold lesions, and adductor spasmodic dysphonia. Compared with the accuracy of human specialists, the overall accuracy rates were 60.1% and 56.1% for the 2 laryngologists and 51.4% and 43.2% for the 2 general ear, nose, and throat doctors. Conclusions Voice alone could be used for common vocal fold disease recognition through a deep learning approach after training with our Mandarin pathological voice database. This approach involving artificial intelligence could be clinically useful for screening general vocal fold disease using the voice. The approach includes a quick survey and a general health examination. It can be applied during telemedicine in areas with primary care units lacking laryngoscopic abilities. It could support physicians when prescreening cases by allowing for invasive examinations to be performed only for cases involving problems with automatic recognition or listening and for professional analyses of other clinical examination results that reveal doubts about the presence of pathologies.

show abstract

Section: Comparison With Prior Workmentioning

confidence: 99%

Deep Learning Application for Vocal Fold Disease Prediction Through Voice Recognition: Preliminary Development Study

Hu¹,

Chang²,

Wang³

et al. 2021

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…This work also uses the SVD, which was recorded by the Institute of Phonetics of the Saarland University in Germany [11]. We use the sustained vowel /a/ sound recorded from each individual at neutral pitch, of which 482 are healthy and 482 are diagnosed with various pathologies (140 laryngitis, 41 leukoplakia, 68 Reinke's edema, 213 recurrent laryngeal nerve paralyses, 22 vocal fold carcinoma, and 45 vocal fold polyps) [6], [8]. The extracted subset is the same as that described in previous studies [6], [8] to enable the comparison of our results with those of the aforementioned previous studies.…”

Section: Databasementioning

confidence: 99%

“…The deep neural network (DNN) algorithm could fully utilize the acoustic features and efficiently differentiate between normal and pathological voice samples [5]. A convolutional neural network (CNN) and short-time Fourier transform (STFT) were used for the reliable classification and feature detection of voice pathologies [6]. Mel-frequency cepstral coefficients (MFCC) derived from the Saarbruecken voice database (SVD) are analyzed using an artificial neural network (ANN) and a support vector machine (SVM).…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Approaches for Pathological Voice Detection Using Heterogeneous Parameters

Lee

Choi

2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

We propose a deep learning-based model for classifying pathological voices using a convolutional neural network and a feedforward neural network. The model uses combinations of heterogeneous parameters, including mel-frequency cepstral coefficients, linear predictive cepstral coefficients and higher-order statistics. We validate the accuracy of this model using the Massachusetts Eye and Ear Infirmary (MEEI) voice disorder database and the Saarbruecken Voice Database (SVD). Our model achieved an accuracy of 99.3% for MEEI and 75.18% for SVD. This model achieved an accuracy that is 7.18% higher than that of competitive models in previous studies.

show abstract

“…Анализ речи используется в логопедии для обнаружения и диагностики речевых нарушений [15,16]. А в перспективе можно будет проводить количественную оценку улучшения состояния речевых функций пациента в процессе и после лечения (в противовес субъективной оценке динамики).…”

Section: анализ речиunclassified

Application of artificial intelligence in medical data analysis

Бурсов

2019

Alʹm. klin. med.

View full text Add to dashboard Cite

Convolutional Neural Networks for Pathological Voice Detection

Cited by 36 publications

References 14 publications

Deep Learning Application for Vocal Fold Disease Prediction Through Voice Recognition: Preliminary Development Study

Deep Learning Application for Vocal Fold Disease Prediction Through Voice Recognition: Preliminary Development Study

Deep Learning Approaches for Pathological Voice Detection Using Heterogeneous Parameters

Application of artificial intelligence in medical data analysis

Contact Info

Product

Resources

About