Topic
Dysarthria
About: Dysarthria is a research topic. Over the lifetime, 2402 publications have been published within this topic receiving 56554 citations.
Papers published on a yearly basis
Papers
More filters
••
28 Jul 2018TL;DR: This work investigates the joint use of articulatory and acoustic features for automatic speech recognition (ASR) of pathological speech with a designated acoustic model, namely a fused-feature-map convolutional neural network (fCNN), which performs frequency convolution on acoustic features and time Convolution on articulatory features.
Abstract: In this work, we investigate the joint use of articulatory and acoustic features for automatic speech recognition (ASR) of pathological speech Despite long-lasting efforts to build speaker- and text-independent ASR systems for people with dysarthria, the performance of state-of-the-art systems is still considerably lower on this type of speech than on normal speech The most prominent reason for the inferior performance is the high variability in pathological speech that is characterized by the spectrotemporal deviations caused by articulatory impairments due to various etiologies To cope with this high variation, we propose to use speech representations which utilize articulatory information together with the acoustic properties A designated acoustic model, namely a fused-feature-map convolutional neural network (fCNN), which performs frequency convolution on acoustic features and time convolution on articulatory features is trained and tested on a Dutch and a Flemish pathological speech corpus The ASR performance of fCNN-based ASR system using joint features is compared to other neural network architectures such conventional CNNs and time-frequency convolutional networks (TFCNNs) in several training scenarios
12 citations
••
TL;DR: Papers dealing with speech production in persons with hearing impairment, aphasia, dysarthria, voice disorders, and structural modifications of the vocal tract, as well as simulations of hearing loss and lexicons show how data from speech and hearing disorders may inform theory about normal processes.
12 citations
•
TL;DR: BST, custom designed to improve nonspeech- and speech-breathing coordination, was followed by LSVT and gains generally were maintained up to 4 months, but were limited by the spastic characteristics of his dysarthria and sporadic medical complications.
Abstract: The Lee Silverman Voice Treatment® (LSVT) program was developed to improve speech in persons with hypokinetic dysarthria associated with Parkinson disease (PD) (Ramig, 1995). It has been tested in a relatively large number of people with PD, and available evidence supports its effectiveness for up to 2 years (Ramig et al., 2001). Less often, LSVT has been used with patients who have other etiologies, including Parkinson-plus syndromes (Countryman, Ramig, & Pawlas, 1994) and multiple sclerosis (Sapir et al., 2001). Results from these cases are guarded by the apparent need to supplement or extend the standard 4-week program and evidence of decreased effectiveness over subsequent months.
Previously, we published a case study of a young man who presented with mixed hypokinetic-spastic dysarthria 20 months post-TBI (Solomon et al., 2001). He participated in LSVT followed by 6 weeks of Combination Treatment that included speech-breathing training, physical therapy, and LSVT-type tasks. The additional treatment was deemed necessary because of minimal improvement in speech breathing and speech intelligibility following LSVT alone. Marked improvements resulted after the full 10-week program, and these gains were maintained for several months. To further examine the viability of LSVT as a treatment strategy for patients with mixed hypokinetic-spastic dysarthria, we replicated the study in a similar patient. In contrast to the previous study, we simplified the Combination Treatment to focus only on nonspeech and speech breathing, conducted treatments in reverse order, and included multiple baseline assessments. Data also were collected after 6 weeks of Breathing-for-Speech Treatment (BST), after the 4-week LSVT program, and 1- and 4-months posttreatment.
12 citations
••
TL;DR: MRI was most helpful in identifying NMD and polymicrogyria in both centroparietal areas in this context and great alertness is needed to identify this disorder to determine the etiology of epilepsy and dysarthria of uncertain origin.
Abstract: The advent of MRI technique has enabled the diagnosis of neuronal migration disorders(NMD) and made it possible to make "in vivo" diagnosis. Congenital bilateral perisylvian syndrome(CBPS) is a recently described disease identify characterized by pseudobulbar palsy, epilepsy, mental retardation, and migration disorders in the bilateral perisylvian area. We have identified four CBPS patients based on neuroimaging and dysarthria patterns among the candidates for epilepsy surgery. All the patients had orofacial diplegia and variable degrees of mental retardation. In the spectrographic analysis of dysarthria, the loss of specific characteristics of formants of vowels and increment of noise in the high frequency formants were observed. Epilepsy was present in all, but only one patient showed intractable seizure requiring surgical intervention. MRI was most helpful in identifying NMD and polymicrogyria in both centroparietal areas in this context. Great alertness is needed to identify this disorder to determine the etiology of epilepsy and dysarthria of uncertain origin.
12 citations
••
06 Sep 2015TL;DR: This work performs initial alignments to locate long pauses in dysarthric speech and make use of the pause intervals as anchor points, and applies speech recognition for word lattice outputs for recovering the time-stamps of the words in disordered or incomplete pronunciations to obtain reliably aligned segments.
Abstract: Dysarthria is a motor speech disorder due to neurologic deficits. The impaired movement of muscles for speech production leads to disordered speech where utterances have prolonged pause intervals, slow speaking rates, poor articulation of phonemes, syllable deletions, etc. These present challenges towards the use of speech technologies for automatic processing of dysarthric speech data. In order to address these challenges, this work begins by addressing the performance degradation faced in forced alignment. We perform initial alignments to locate long pauses in dysarthric speech and make use of the pause intervals as anchor points. We apply speech recognition for word lattice outputs for recovering the time-stamps of the words in disordered or incomplete pronunciations. By verifying the initial alignments with word lattices, we obtain the reliably aligned segments. These segments provide constraints for new alignment grammars, that can improve alignment and transcription quality. We have applied the proposed strategy to the TORGO corpus and obtained improved alignments for most dysarthric speech data, while maintaining good alignments for non-dysarthric speech data. Index Terms: automatic forced alignment, speech recognition, dysarthric speech, word lattices
12 citations