Transfer learning helps to improve the accuracy to classify patients with different speech disorders in different languages

Vásquez-Correa, Juan Camilo; Ríos-Urrego, Cristian David; Arias-Vergara, Tomás; Schuster, Maria; Rusz, Ján; Nöth, Elmar; Orozco-Arroyave, Juan Rafael

doi:10.1016/j.patrec.2021.04.011

Cited by 19 publications

(19 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With lower standard deviations of cross-validation results and higher balance in terms of sensitivity and specificity, a classifier based on gradient trees can be considered suitable when dealing with multilingual data. Vasquez-Correa et al [36] also observed a lower difference between sensitivity and specificity and lower standard deviation of cross-validation results when fine-tuning the deep machine learning model. This implies that the model trained on more data has a more balanced classification despite the language differences when choosing an appropriate machine learning approach.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Exploring Digital Speech Biomarkers of Hypokinetic Dysarthria in a Multilingual Cohort

Kovac

Mekyska

Aharonson

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Motor speech disorders in patients with Parkinson’s disease (PD), collectively referred to as hypokinetic dysarthria, are the early markers of the disease. Acoustic speech features are, therefore, suitable digital biomarkers for the diagnosis and monitoring of this pathological phenomenon. At the same time, it is clear that language plays an essential role in using these features to classify speech successfully into healthy and dysarthric one. This paper focuses on the multilingual analysis of the currently used and newly proposed acoustic speech features and their use in the supportive diagnosis of PD. The goal is to explore digital speech biomarkers of PD, focusing on their language independence and high discrimination power using statistical analysis and machine learning techniques. Thirty-three acoustic features of Czech, American, Israeli, Columbian and Italian PD patients and healthy controls were analyzed using correlation and statistical tests, descriptive statistics, and the XGBoost classifier with posterior explanation by features importances and Shapley values. The features quantifying the prominence of the second formant, monopitch, and the lower number of pauses detected during text reading show the best results, both by statistical analysis and machine learning. Classification accuracies range from 67% to 85%, depending on the language. The paper introduces the concept of language robustness as a quality in which a feature behaves the same, independently of the language. By using this new concept along with other metrics, it proposes several digital speech biomarkers that have the potential to be language-independent with high discrimination power.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Vásquez-Correa et al (2019) [26] used convolution neural nets and transfer learning strategy to classify PD in Spanish, German and Czech with MFCC and BBE as input independent variables. Accuracy ranged between 70 % and 77 %.…”

Section: Introductionmentioning

confidence: 99%

Exploring Digital Speech Biomarkers of Hypokinetic Dysarthria in a Multilingual Cohort

Kovac

Mekyska

Aharonson

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the case of a limited size dataset, transfer learning is used to relax the hypothesis that the training data must be large, independent and identically distributed with the test data. This motivates many work [68], [69], [70], [71], [72], [73] to use transfer learning in the presence of insufficient training data for speech and language classification. A network, which is pretrained on a large-sized dataset, such as the ImageNet [74], will keep its structure and connection parameters, when used by a network-based deep transfer learning, to compute intermediate image representations for smaller-sized datasets.…”

Section: B Machine Learning Modelsmentioning

confidence: 99%

Building an Arabic Dialectal Diagnostic Dataset for Healthcare

Mounsef¹,

Hasib²,

Raza³

2022

IJACSA

View full text Add to dashboard Cite

Accurate diagnosis of patient conditions becomes challenging for medical practitioners in urban metropolitan cities. A variety of languages and spoken dialects impedes the diagnosis achieved through the exploratory journey a medical practitioner and patient go through. Natural language processing has been used in well-known applications, such as Google Translate, as a solution to reduce language barriers. Languages typically encountered in these applications provide the most commonly known, used or standardized dialect. The Arabic language can benefit from the common dialect, which is available in such applications. However, given the diversity of dialects in Arabic in the healthcare domain, there is a risk associated with incorrect interpretation of a dialect, which can impact the diagnosis or treatment of patients. Arabic language dialect corpuses published in recent research work can be applied to rule-based natural language applications. Our study aims to develop an approach to support medical practitioners by ensuring that the diagnosis is not impeded based on the misinterpretation of patient responses. Our initial approach reported in this work adopts the methods used by practitioners in the diagnosis carried out within the scope of the Emirati and Egyptian Arabic dialects. In this paper, we develop and provide a public Arabic Dialect Dataset (ADD), which is a corpus of audio samples related to healthcare. In order to train machine learning models, the dataset development is designed with multi-class labelling. Our work indicates that there is a clear risk of bias in datasets, which may come about when a large number of classes do not have enough training samples. Our crowd sourcing solution presented in this work may be an approach to overcome the sourcing of audio samples. Models trained with this dataset may be used to support the diagnosis made by medical practitioners.

show abstract

“…In practical applications, Transfer learning models are quite commonly used to improve the accuracy of deep learning models. Specifically in this regard, some studies can be mentioned such as: the problem of identifying patients with Parkinson's disease [1], predicting air quality at large time resolution [2], using VGG-16 classifies retinopathy caused by diabetes [3], improving the process of sleep organization method [4], improving ad accuracy by checking clicks [5], improving the accuracy in counting the number of wheat ears [6], improving the accuracy in classifying medicinal leaves [7], classifying diseases in poultry [8], etc. In general, when using a Transfer learning model with different data sets, the accuracy of the model is also significantly improved when the accuracy increases from 5-8%.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of the Efficiency of the Optimization Algorithms for Transfer Learning on the Rice Leaf Disease Dataset

Quach¹,

Quoc²,

Quynh³

et al. 2022

IJACSA

View full text Add to dashboard Cite

To improve the model's efficiency, people use many different methods, including the Transfer Learning algorithm, to improve the efficiency of recognition and classification of image data. The study was carried out to combine optimization algorithms with the Transfer Learning model with MobileNet, MobileNetV2, InceptionV3, Xception, ResNet50V2, DenseNet201 models. Then, testing on rice disease data set with 13.186 images, background removed. The result obtained with high accuracy is the RMSprop algorithm, with an accuracy of 88% when combined with the Xception model, similar to the F1, Xception model, and ResNet50V2 score of 87% when combined with the Adam algorithm. This shows the effect of gradients on the Transition learning model. Research, evaluate and draw the optimal model to build a website to identify diseases on rice leaves, with the main functions including images and recording of disease identification points for better management purposes on diseased areas of rice.

show abstract

Transfer learning helps to improve the accuracy to classify patients with different speech disorders in different languages

Cited by 19 publications

References 22 publications

Exploring Digital Speech Biomarkers of Hypokinetic Dysarthria in a Multilingual Cohort

Exploring Digital Speech Biomarkers of Hypokinetic Dysarthria in a Multilingual Cohort

Building an Arabic Dialectal Diagnostic Dataset for Healthcare

Evaluation of the Efficiency of the Optimization Algorithms for Transfer Learning on the Rice Leaf Disease Dataset

Contact Info

Product

Resources

About