Dysarthria

About: Dysarthria is a research topic. Over the lifetime, 2402 publications have been published within this topic receiving 56554 citations.

Isolated hypoglossal nerve palsy caused by neurovascular compression.

Abstract: An 80-year-old man presented with difficulty in swallowing and speaking which had progressed over one year. Neurological examination revealed right hypoglossal nerve palsy with ipsilateral atrophy (Picture A). Laryngoscopic examination was unremarkable. Slowly progressive dysarthria and dysphagia with tongue atrophy initially indicated motor neuron disease (MND), but needle electromyographic examination did not show neurogenic changes consistent with MND. Brain MRI showed mild deep white matter lesions without space occupying lesions. Constructive interference in steady state (CISS) MRI showed right vertebral artery compression in the medulla oblongata, which corresponded to the exit of the right hypoglossal nerve (Picture B). The indication for surgical decompression is currently under consideration. Although isolated hypoglossal nerve palsy can be caused by different etiologies (1), neurovascular compression is an important cause, given that microvascular decompression can resolve hypoglossal nerve palsy (2). Physicians should be

Improved ASR Performance for Dysarthric Speech Using Two-stage DataAugmentation

Abstract: Machine learning (ML) and Deep Neural Networks (DNN) have greatly aided the problem of Automatic Speech Recognition (ASR). However, accurate ASR for dysarthric speech remains a serious challenge. Dearth of usable data remains a problem in applying ML and DNN techniques for dysarthric speech recognition. In the current research, we address this challenge using a novel two-stage data augmentation scheme, a combination of static and dynamic data augmentation techniques that are designed by leveraging an understanding of the characteristics of dysarthric speech. Deep Autoencoder (DAE)-based healthy speech modification and various perturbations comprise static augmentations, whereas SpecAugment techniques modified to specifically augment dysarthric speech comprise the dynamic data augmentation. The objective of this work is to improve the ASR performance for dysarthric speech using the two-stage data augmentation scheme. An end-to-end ASR using a Transformer acoustic model is used to evaluate the data augmentation scheme on speech from the UA dysarthric speech corpus. We achieve an absolute improvement of 16% in word error rate (WER) over a baseline with no augmentation, with a final WER of 20.6% .

Acoustic analysis of Korean stop sounds in patients with dysarthrias

Abstract: Dysarthria is a motor speech disorder that occurs due to abnormalities in the central and/or peripheral nervous system. The speed, strength, range, steadiness, and tone of motor speech behaviors are affected by the abnormal performances of nerve fibers and muscles [1,2]. This disorder is known to influence five speech components, including respiration, phonation, articulation, prosody, and resonance [1,2]. Because all phonemes in the language are influenced by the disorder, the overall intelligibility, rather than the percentage of correctly produced consonants, has been of interest to both clinicians and researchers. “Speech intelligibility” is a measurement that scores how much listeners can underPurpose: Korean ‘stops’ are considered an especially good acoustic variable since they are sensitive to speech intelligibility and reflect physiological coordination between laryngeal and supra-laryngeal mechanisms. The purpose of the study was to evaluate the acoustic characteristics of both the dysarthria and control groups in the production of nine Korean stops, /p, p', p, t, t', t, k, k', k/, in VCV contexts. Methods: The participants comprised eight patients with dysarthria and eight ageand gender-matched normal adults. After the acoustic analysis of the closure duration, aspiration duration, and the ratio of closure duration to closure-aspiration combined duration, the results were compared among three types of phonation and places of articulation for Korean stops.

Hypokinetic dysarthria and palilalia in midbrain infarction

Abstract: Dysarthria is a speech disturbance that often occurs following brain damage. The characteristics of dysarthria, however, differ according to the location of the lesion. Hypokinetic dysarthria and palilalia are closely associated with basal ganglionic dysfunction, which is common in patients with Parkinson’s disease (PD). In this report, we present a patient who showed these speech problems after left midbrain infarction. The speech disturbance observed in this patient may be caused by the same underlying mechanism as occurs in PD. A 55-year-old diabetic, right-handed woman was admitted to the Asan Medical Centre after suddenly developing diplopia. She was a homemaker with 9 years of education. She had no history of stroke or other brain injury. On neurological examination, she showed left third nerve palsy sparing the pupil, clumsiness in the right arm and slight gait instability. Prominent dysarthria was noted. Muscle strength and sensory perception were normal in the extremities as well as in the face. Although there was slight ataxia in the right extremities, she was able to walk without difficulty. Her facial expressions were normal, and there was no …

Impact of Cognitive Impairment and Dysarthria on Spoken Language in Multiple Sclerosis.

Abstract: Objective: To investigate the impact of cognitive impairment on spoken language produced by speakers with multiple sclerosis (MS) with and without dysarthria. Method: Sixty speakers comprised operationally defined groups. Speakers produced a spontaneous speech sample to obtain speech timing measures of speech rate, articulation rate, and silent pause frequency and duration. Twenty listeners judged the overall perceptual severity of the samples using a visual analog scale that ranged from no impairment to severe impairment (speech severity). A 2 × 2 factorial design examined main and interaction effects of dysarthria and cognitive impairment on speech timing measures and speech severity in individuals with MS. Each speaker group with MS was further compared to a healthy control group. Exploratory regression analyses examined relationships between cognitive and biopsychosocial variables and speech timing measures and perceptual judgments of speech severity, for speakers with MS. Results: Speech timing was significantly slower for speakers with dysarthria compared to speakers with MS without dysarthria. Silent pause durations also significantly differed for speakers with both dysarthria and cognitive impairment compared to MS speakers without either impairment. Significant interactions between dysarthria and cognitive factors revealed comorbid dysarthria and cognitive impairment contributed to slowed speech rates in MS, whereas dysarthria alone impacted perceptual judgments of speech severity. Speech severity was strongly related to pause duration. Conclusions: The findings suggest the nature in which dysarthria and cognitive symptoms manifest in objective, acoustic measures of speech timing and perceptual judgments of severity is complex.