In this paper, we propose a multi-scale mel domain feature map extraction algorithm to solve the problem that the speech recognition rate of dysarthria is difficult to improve. We used the empirical mode decomposition method to decompose speech signals and extracted Fbank features and their first-order differences for each of the three effective components to construct a new feature map, which could capture details in the frequency domain. Secondly, due to the problems of effective feature loss and high computational complexity in the training process of single channel neural network, we proposed a speech recognition network model in this paper. Finally, training and decoding were performed on the public UA-Speech dataset. The experimental results showed that the accuracy of the speech recognition model of this method reached 92.77%. Therefore, the algorithm proposed in this paper can effectively improve the speech recognition rate of dysarthria.
Humans ; Dysarthria/diagnosis* ; Speech ; Speech Perception ; Algorithms ; Neural Networks, Computer

The cleft lip and palate (CLP) is one of the most common craniofacial malformations in humans. We collected functional magnetic resonance data of 23 CLP patients before rehabilitation training (Bclp) and 23 CLP patients after rehabilitation training (Aclp), who were performing Chinese character pronunciation tasks, and performed brain activation analysis to explore the changes of brain mechanism in CLP patients after articulation disorder rehabilitation training. The study found that Aclp group had significant activation in the motor cortex, Broca area, Wernicke area and cerebellum. While the Bclp group had weak activation in the motor cortex with a small activation range. By comparing the differences and co-activated brain regions between the two groups, we found that rehabilitation training increased the activity level of negatively activated brain areas (cerebellum, left motor area, Wernicke area, etc.) to a positive level. At the same time, the activity level of weakly activated brain areas (right motor area, Broca area, etc.) was also increased. Rehabilitation training promoted the activity level of articulation-related brain regions. So that the activation intensity of articulation-related brain regions can be used as a quantifiable objective evaluation index to evaluate the effect of rehabilitation training, which is of great significance for the formulation of rehabilitation training programs.
Humans ; Articulation Disorders/therapy* ; Brain/diagnostic imaging* ; Cleft Lip/diagnostic imaging* ; Cleft Palate/diagnostic imaging* ; Magnetic Resonance Imaging ; Speech Therapy/psychology*

INTRODUCTION: The National Institutes of Health Stroke Scale (NIHSS), originally designed in the United States of America, contains items on dysphasia and dysarthria that are deemed culturally unsuitable for the Singapore context. We compared the error rates of dysphasia objects, dysphasia phrases and dysarthria words between the original and alternative items in a cohort of Singaporean subjects without dysphasia or dysarthria. METHODS: In this prospective study, 140 English-speaking Singaporean subjects without impairments of dysphasia or dysarthria had an assessment of NIHSS items 9 and 10 using the original and alternative items. Paired analyses were conducted for comparison of error rates. RESULTS: The error rates were high for four original dysphasia objects (Hammock: 62.9%, Cactus: 38.6%, Feather: 23.6%, Glove: 20.7%) and significantly lower for alternative items (Snail: 5%, Horse: 1.4%, Hanger: 1.4%, Car: 0%) (P < 0.001). For dysphasia phrases and dysarthria words, the error rates were low and there were no differences in error rates between the original and alternative items. CONCLUSION There are cultural issues with several dysphasia objects in the original NIHSS as evidenced by the high error rates, which were lowered with more culturally suitable alternatives. This study formed a basis to derive a more suitable version of the NIHSS for English-speaking subjects in Singapore.
Humans ; United States ; Animals ; Horses ; Stroke/diagnosis* ; Singapore ; Dysarthria/diagnosis* ; Prospective Studies ; National Institutes of Health (U.S.) ; Aphasia/diagnosis* ; Severity of Illness Index

A boy, aged 2 years and 4 months, had a sudden onset of blepharoptosis of the right eyelid, accompanied by the mouth deviated to the right side, drinking cough, nystagmus, and developmental regression. Cranial MRI showed softening lesions formed after infarction of the right dorsolateral medulla oblongata, while head CT angiography showed no imaging of the proximal part of the V4 segment of the right vertebral artery. The child was diagnosed with dorsolateral medulla oblongata syndrome and was treated with gamma globulin to regulate immune function, with mannitol to reduce neuronal edema, with low-molecular-weight heparin sodium to improve local hypercoagulation of occluded blood vessels, with hyperbaric oxygen to improve local ischemia and hypoxia and promote the recovery of brain function, and with neuromuscular electrical stimulation to promote the recovery of neuromuscular function. Before discharge, only mild right ataxia and Horner syndrome remained. This article reports the first case of infantile dorsolateral medulla oblongata syndrome and provides experience for the diagnosis and treatment of the disease.
Blepharoptosis/etiology* ; Child, Preschool ; Dysarthria/etiology* ; Humans ; Lateral Medullary Syndrome/diagnosis* ; Magnetic Resonance Imaging ; Male ; Medulla Oblongata/diagnostic imaging*

OBJECTIVE: To evaluate correlations between values of articulation tests and language tests for children with articulation disorder in Korea. METHODS: Data of outpatients with chief complaint of an articulation problem were retrospectively collected. Patients who underwent Urimal Test of Articulation and Phonation (U-TAP) with Assessment of Phonology and Articulation for Children (APAC), Preschool Receptive-Expressive Language Scale (PRES), or Receptive and Expressive Vocabulary Test (REVT) simultaneously were identified. Patients whose word-level percentages of correct consonants in U-TAP (UTAP_wC) were more than 2 standard deviations below the mean as diagnostic criteria for articulation disorder were selected. Those whose receptive language age (P_RLA), expressive language age (P_ELA), or combined language age (P_CLA) in PRES was delayed more than 24 months compared to their chronological age in months as diagnostic criteria for language disorder were excluded. RESULTS: Thirty-three children aged 3–6 years were enrolled retrospectively. PRES and U-TAP showed significant correlations for most of value relationships. PRES and APAC showed significant correlations for all value relationships except for receptive language age. All values of REVT were significantly correlated with all values from U-TAP, but not with any value from APAC. Articulation tests U-TAP and APAC showed significant correlations between percentages of correct consonants. Language tests PRES and REVT showed significant correlations for all value relationships. CONCLUSION: This study suggests that articulation abilities and language abilities might be correlated in children with articulation disorder.
Articulation Disorders ; Child ; Humans ; Korea ; Language ; Language Disorders ; Language Tests ; Outpatients ; Phonation ; Retrospective Studies ; Speech Articulation Tests ; Speech Disorders

Macroglossia is a rare clinical condition defined as an enlarged tongue. Macroglossia can cause structural deformities like diastema and disproportionate mandibular growth and present functional disorders such as dysarthria, dysphonia, and respiratory problems. A 7-year-old boy who had lymphangiomatous macroglossia was treated with a reduction glossectomy by anchor-shaped combination of a U-shape and modified key-hole resection. Postoperatively, the reduced tongue was contained completely within the oral cavity, but open bite remained due to prognathism. Sensory and motor nerves to the tongue appeared to be intact, and circulation was adequate. This patient will be monitored for recurrence of tongue enlargement.
Child ; Congenital Abnormalities ; Diastema ; Dysarthria ; Dysphonia ; Glossectomy ; Humans ; Lymphangioma ; Macroglossia ; Male ; Mouth ; Open Bite ; Prognathism ; Recurrence ; Tongue

BACKGROUND AND PURPOSE: Neurological involvement in Behçet's disease [neuro-Behçet's disease (NBD)] is uncommon, but it is worth investigating since it can cause substantial disability. However, difficulties exist in understanding the clinical features of NBD due to regional variations and the lack of studies utilizing well-established diagnostic criteria. We therefore analyzed the clinical features of patients with NBD based on the recent international consensus recommendation. METHODS: We retrospectively searched electronic databases for patients with Behçet's disease (BD) between 2000 and 2017, and reviewed their medical records. Based on the recent international consensus recommendation, patients with definite or probable NBD were included. RESULTS: Of 9,817 patients with the diagnosis code for BD, 1,682 (17.1%) visited the neurology clinic and 110 (1.1%) were classified as NBD. Ninety-eight patients exhibited parenchymal NBD and 12 exhibited nonparenchymal NBD. Their age at the onset of NBD was 37.6±10.6 years and the male-to-female ratio was 1.24:1. Brainstem syndrome (43.9%) was the most common condition in the 98 patients with parenchymal NBD, followed by multifocal (32.7%) and spinal cord (12.2%) syndromes. 72.4% exhibited acute NBD and 27.6% exhibited a progressive disease course. Frequent manifestations included pyramidal signs (52.0%), headache (45.9%), dysarthria (42.9%), and fever (31.6%). A frequent pattern in brain MRI was an upper brainstem lesion extending to the thalamus and basal ganglia. CONCLUSIONS: Approximately 1% of the patients with suspected BD exhibited NBD. Neurologists must understand the clinical characteristics of NBD in order to perform the differential diagnosis and management of these patients.
Basal Ganglia ; Brain ; Brain Stem ; Classification ; Consensus ; Diagnosis ; Diagnosis, Differential ; Dysarthria ; Fever ; Headache ; Humans ; Korea ; Magnetic Resonance Imaging ; Medical Records ; Neurology ; Retrospective Studies ; Spinal Cord ; Thalamus

BACKGROUND: The gold standard in dysarthria assessment involves subjective analysis by a speech–language pathologist (SLP). We aimed to investigate the feasibility of dysarthria assessment using automatic speech recognition. METHODS: We developed an automatic speech recognition based software to assess dysarthria severity using hidden Markov models (HMMs). Word-specific HMMs were trained using the utterances from one hundred healthy individuals. Twenty-eight patients with dysarthria caused by neurological disorders, including stroke, traumatic brain injury, and Parkinson's disease were participated and their utterances were recorded. The utterances of 37 words from the Assessment of Phonology and Articulation for Children test were recorded in a quiet control booth in both groups. Patients were asked to repeat the recordings for evaluating the test–retest reliability. Patients' utterances were evaluated by two experienced SLPs, and the consonant production accuracy was calculated as a measure of dysarthria severity. The trained HMMs were also employed to evaluate the patients' utterances by calculating the averaged log likelihood (aLL) as the fitness of the spoken word to the word-specific HMM. RESULTS: The consonant production accuracy reported by the SLPs strongly correlated (r = 0.808) with the aLL, and the aLL showed excellent test–retest reliability (intraclass correlation coefficient, 0.964). CONCLUSION: This leads to the conclusion that dysarthria assessment using a one-word speech recognition system based on word-specific HMMs is feasible in neurological disorders.
Brain Injuries ; Child ; Dysarthria ; Humans ; Nervous System Diseases ; Parkinson Disease ; Stroke

Supratentorial extraventricular anaplastic ependymoma (SEAE) in adults is a relatively rare intracranial tumor. Because of the very low prevalence, only a few cases have been reported. According to a recent study, SEAE is associated with a poor prognosis and there is no definite consensus on optimal treatment. We report a case of an adult SEAE patient who had no recurrence until seven years after a gross total resection (GTR) followed by conventional radiotherapy. A 42-year-old male had a persistent mild headache, left facial palsy, dysarthria, and left hemiparesis. Preoperative neuroimaging revealed an anaplastic astrocytoma or supratentorial ependymoma in the right frontal lobe. A GTR was performed, followed by adjuvant radiotherapy. Histologic and immunohistochemical results revealed anaplastic ependymoma. After seven years of initial therapy, a regular follow-up MRI showed a 3-cm-sized partially cystic mass in the same area as the initial tumor. The patient underwent a craniotomy, and a GTR was performed. Histopathologic examination revealed recurrence of the SEAE. External radiotherapy was performed. The patient has been stable without any disease progression or complications for 12 months since the surgery for recurrent SEAE.
Adult ; Astrocytoma ; Consensus ; Craniotomy ; Disease Progression ; Dysarthria ; Ependymoma ; Facial Paralysis ; Follow-Up Studies ; Frontal Lobe ; Headache ; Humans ; Magnetic Resonance Imaging ; Male ; Neuroimaging ; Paresis ; Prevalence ; Prognosis ; Radiotherapy ; Radiotherapy, Adjuvant ; Recurrence ; Supratentorial Neoplasms

We describe a 33-year-old woman with chronic bulbar dysarthria after ischemic brainstem stroke who underwent a new form of constraint-induced therapy, namely constraint-induced dysarthria therapy, based on three principles: avoidance of supportive devices, intensive therapy, and gradually augmenting difficulty. After a 2-month intervention, improvement was noted for speech intelligibility, fluency, and intensity. This led to increased communicative participation, including during conversation situations, which has been maintained over a 12-month follow-up.
Adult ; Brain Stem Infarctions ; Dysarthria ; Female ; Follow-Up Studies ; Humans ; Speech Intelligibility ; Stroke