Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ https://zenodo.org/r...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
https://zenodo.org/record/3673...
Part of book or chapter of book
License: CC BY
Data sources: UnpayWall
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Conference object . 2019
License: CC BY
Data sources: ZENODO
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
https://doi.org/10.1007/978-3-...
Part of book or chapter of book . 2018 . Peer-reviewed
License: Springer TDM
Data sources: Crossref
http://dx.doi.org/10.1007/978-...
Part of book or chapter of book
License: Springer TDM
Data sources: Sygma
https://dx.doi.org/10.60692/19...
Other literature type . 2018
Data sources: Datacite
https://dx.doi.org/10.60692/s9...
Other literature type . 2018
Data sources: Datacite
DBLP
Conference object
Data sources: DBLP
versions View all 7 versions
addClaim

Phonological i-Vectors to Detect Parkinson’s Disease

المتجهات الصوتية للكشف عن مرض باركنسون
Authors: Nicanor García-Ospina; Tomás Arias‐Vergara; Juan Camilo Vásquez-Correa; Juan Rafael Orozco-Arroyave; Miloš Cerňak; Elmar Nöth;

Phonological i-Vectors to Detect Parkinson’s Disease

Abstract

Les troubles de la parole sont des symptômes courants chez les patients atteints de la maladie de Parkinson et affectent la parole des patients sous différents aspects. À l'heure actuelle, peu d'études prennent en compte la dimension phonologique de la parole de Parkinson. Dans ce travail, nous utilisons une méthode récemment développée pour extraire les caractéristiques phonologiques des signaux vocaux. Ces caractéristiques sont basées sur les modèles sonores du modèle phonologique anglais. L'extraction est effectuée à l'aide de réseaux neuronaux profonds pré-entraînés pour déduire les probabilités de caractéristiques phonologiques à partir de caractéristiques acoustiques de courte durée. Un extracteur i-vecteur est entraîné avec les caractéristiques phonologiques. Les i-vecteurs extraits sont utilisés pour classer les patients et les locuteurs sains et évaluer leur état neurologique et leur niveau de dysarthrie. Cette approche pourrait être utile pour évaluer de nouveaux aspects spécifiques de la parole tels que le mouvement des différents articulateurs impliqués dans le processus de production de la parole.

Los trastornos del habla son síntomas comunes entre los pacientes con enfermedad de Parkinson y afectan el habla de los pacientes en diferentes aspectos. Actualmente, hay pocos estudios que consideren la dimensión fonológica del habla de Parkinson. En este trabajo, utilizamos un método recientemente desarrollado para extraer características fonológicas de las señales del habla. Estas características se basan en los patrones de sonido del modelo fonológico inglés. La extracción se realiza utilizando redes neuronales profundas preentrenadas para inferir las probabilidades de características fonológicas a partir de características acústicas de corta duración. Un extractor i-vector está entrenado con las características fonológicas. Los i-vectores extraídos se utilizan para clasificar pacientes y hablantes sanos y evaluar su estado neurológico y nivel de disartria. Este enfoque podría ser útil para evaluar nuevos aspectos específicos del habla, como el movimiento de los diferentes articuladores involucrados en el proceso de producción del habla.

Speech disorders are common symptoms among Parkinson's disease patients and affect the speech of patients in different aspects. Currently, there are few studies that consider the phonological dimension of Parkinson's speech. In this work, we use a recently developed method to extract phonological features from speech signals. These features are based on the Sound Patterns of English phonological model. The extraction is performed using pre-trained Deep Neural Networks to infer the probabilities of phonological features from short-time acoustic features. An i-vector extractor is trained with the phonological features. The extracted i-vectors are used to classify patients and healthy speakers and assess their neurological state and dysarthria level. This approach could be helpful to assess new specific speech aspects such as the movement of different articulators involved in the speech production process.

اضطرابات النطق هي أعراض شائعة بين مرضى الشلل الرعاش وتؤثر على كلام المرضى في جوانب مختلفة. في الوقت الحالي، هناك عدد قليل من الدراسات التي تأخذ في الاعتبار البعد الصوتي لخطاب باركنسون. في هذا العمل، نستخدم طريقة تم تطويرها مؤخرًا لاستخراج السمات الصوتية من إشارات الكلام. تعتمد هذه الميزات على أنماط الصوت للنموذج الصوتي الإنجليزي. يتم إجراء الاستخراج باستخدام شبكات عصبية عميقة مدربة مسبقًا لاستنتاج احتمالات الميزات الصوتية من الميزات الصوتية قصيرة الوقت. يتم تدريب المستخرج i - vector على الميزات الصوتية. تُستخدم الناقلات المستخرجة لتصنيف المرضى والمتحدثين الأصحاء وتقييم حالتهم العصبية ومستوى عسر الكلام. يمكن أن يكون هذا النهج مفيدًا لتقييم جوانب محددة جديدة للكلام مثل حركة المفصلات المختلفة المشاركة في عملية إنتاج الكلام.

Keywords

Artificial intelligence, Physiology, Social Sciences, Extractor, Experimental and Cognitive Psychology, Diagnosis and Treatment of Voice Disorders, Speech recognition, Phonology, Engineering, Artificial Intelligence, Health Sciences, FOS: Mathematics, Psychology, Speaker Diarization, Speech production, Dysarthria, Natural language processing, Pure mathematics, Linguistics, Audiology, Speaker Verification, Computer science, FOS: Philosophy, ethics and religion, FOS: Psychology, Speech Recognition Technology, Philosophy, Speech Perception and Phonetics, Voice Training, Dimension (graph theory), FOS: Biological sciences, Computer Science, Physical Sciences, Phonological rule, Speech Perception, FOS: Languages and literature, Medicine, Process engineering, Articulatory Phonetics, Mathematics

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    2
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 3
    download downloads 12
  • 3
    views
    12
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
2
Average
Average
Average
3
12
Green