Automatic voice analysis for dysphagia detection

López-de-Ipiña, Karmele; Calvo, Pilar M.; Faundez-Zanuy, Marcos; Clavé, Père; Nascimento, Weslania Viviane; Lizarduy, Unai Martinez de; Alvarez, D.; Arreola, Viridiana; Ortega, Omar; Mekyska, Jiří; Sanz-Cartagena, P

doi:10.1080/2050571x.2017.1369017

Cited by 8 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Other authors have also investigated the effect of Parkinson's disease on speech [15] or various aspects of speech deterioration caused by Alzheimer's disease [16], dysphagia [8], or impaired speech [17].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Approach to Dysphonia Detection

et al. 2018

View full text Add to dashboard Cite

This paper addresses the processing of speech data and their utilization in a decision support system. The main aim of this work is to utilize machine learning methods to recognize pathological speech, particularly dysphonia. We extracted 1560 speech features and used these to train the classification model. As classifiers, three state-of-the-art methods were used: K-nearest neighbors, random forests, and support vector machine. We analyzed the performance of classifiers with and without gender taken into account. The experimental results showed that it is possible to recognize pathological speech with as high as a 91.3% classification accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

“…This is usually due to damage of the neurological system or caused directly by damage to some part of the vocal tract, such as the vocal cords [7]. Frequently, a speech disorder leads to a secondary symptom, and early detection may reveal many high-risk illnesses [1,8].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Approach to Dysphonia Detection

et al. 2018

View full text Add to dashboard Cite

show abstract

“…En contraste con lo hallado en [15], se determinó que hay características acústicas o fonatorias con potencial capacidad de diferenciar entre pacientes y controles, hallazgo similar a lo reportado en [44], además de una posible diferenciación entre pacientes con distintos trastornos de voz. En un análisis preliminar también se emplearon las características que se usaron en este estudio de fonación y en el que presentaron que las combinaciones entre estas características muestran gran potencial en su uso como factores de diferenciación en pacientes con disfagia [45].…”

Section: Fonación En Vocales Sostenidasunclassified

Correlación entre espacios de características acústicas del habla y trastornos clínicos de la voz en pacientes con disfagia

Flórez-Gómez

Orozco-Arroyave

Roldan-Vasco

2022

TecnoL.

View full text Add to dashboard Cite

La disfagia se define como la dificultad para transportar un bolo alimenticio de forma segura y efectiva desde la cavidad oral hasta el estómago. En la actualidad, los métodos para el diagnóstico de la disfagia son invasivos y altamente dependientes de la experiencia del personal asistencial cualificado. El estudio de las bioseñales, como lo son los registros de voz y habla, ha sido propuesto con el fin de desarrollar herramientas complementarias al diagnóstico. De esta manera, el presente trabajo tuvo como objetivo explorar, en características extraídas en señales de voz y habla, la capacidad de discriminación entre personas sanas y pacientes con trastornos deglutorios. Para ello se registraron señales en un grupo de 30 personas sanas y 45 pacientes diagnosticados con disfagia. Los participantes realizaron diferentes tareas de voz (vocales sostenidas) y de habla (texto leído, monólogo y ejercicios diadococinéticos). Los registros de los pacientes fueron etiquetados en tres condiciones clínicas: voz húmeda, voz disfónica y voz con alteración no determinada. Se evaluaron espacios de características clásicas asociadas al análisis de voz y habla a través de pruebas estadísticas hallándose que las características relacionadas a la fonación, prosodia y diadococinesia tienen potencial como biomarcadores para la discriminación de diferentes alteraciones en pacientes con disfagia. Este trabajo constituye una aproximación preliminar basada en el estudio de señales de voz y habla para un diagnóstico no invasivo y objetivo de la disfagia.

show abstract

“…[10] performed acoustic analysis of swallowing sounds, using a microphone and a notebook computer system, and claimed that its technique could be incorporated into bedside evaluation. [11] developed an automatic voice analysis system for dysphagia detection which through analysing the acoustic features prior to and immediately following swallowing liquids of varying viscosity and volume. [12] investigated the feasibility of identifying aspiration risk through analysing the acoustic voice parameters of a sustained vowel /a/ for before and after swallowing.…”

Section: Introductionmentioning

confidence: 99%

Smart Dysphagia Detection System with Adaptive Boosting Analysis of Throat Signals

Wang

Jiang

Zhao

et al. 2021

2021 IEEE International Symposium on Circuits and Systems (ISCAS)

View full text Add to dashboard Cite

Dysphagia is a symptom of many neurological disorders. Existing diagnosis systems are either invasive or require swallowing liquids, which are costly and harmful to humans. In this work, we design a smart dysphagia detection system based on speech signals. Rather than the voice data acquired by traditional microphones, we apply a bone conduction headset for vibration signal acquisition from the throat to get cleaner speech signals.After speech feature extraction, under-sampling is performed to deal with the imbalanced data problem, and principal component analysis is used for dimensionality reduction. In this paper, we construct an ensemble adaptive boosting classifier to detect the dysphagia patient. Experimental results show that the testing classification accuracy of the proposed system reaches 71.2%. Sensitivity and specificity can reach 66.6 % and 76 %, respectively.

show abstract

Automatic voice analysis for dysphagia detection

Cited by 8 publications

References 11 publications

Machine Learning Approach to Dysphonia Detection

Machine Learning Approach to Dysphonia Detection

Correlación entre espacios de características acústicas del habla y trastornos clínicos de la voz en pacientes con disfagia

Smart Dysphagia Detection System with Adaptive Boosting Analysis of Throat Signals

Contact Info

Product

Resources

About