Showing papers on "Dysarthria published in 2014"
TL;DR: This work reports the first bilateral probabilistic map for crucial cortical epicentres of human brain functions in the right and left hemispheres, including sensory, motor, and language (speech, articulation, phonology and semantics), which challenge classical theories of brain organization and provide a distributed framework for future studies of neural networks.
Abstract: The organization of basic functions of the human brain, particularly in the right hemisphere, remains poorly understood. Recent advances in functional neuroimaging have improved our understanding of cortical organization but do not allow for direct interrogation or determination of essential (versus participatory) cortical regions. Direct cortical stimulation represents a unique opportunity to provide novel insights into the functional distribution of critical epicentres. Direct cortical stimulation (bipolar, 60 Hz, 1-ms pulse) was performed in 165 consecutive patients undergoing awake mapping for resection of low-grade gliomas. Tasks included motor, sensory, counting, and picture naming. Stimulation sites eliciting positive (sensory/motor) or negative (speech arrest, dysarthria, anomia, phonological and semantic paraphasias) findings were recorded and mapped onto a standard Montreal Neurological Institute brain atlas. Montreal Neurological Institute-space functional data were subjected to cluster analysis algorithms (K-means, partition around medioids, hierarchical Ward) to elucidate crucial network epicentres. Sensorimotor function was observed in the pre/post-central gyri as expected. Articulation epicentres were also found within the pre/post-central gyri. However, speech arrest localized to ventral premotor cortex, not the classical Broca's area. Anomia/paraphasia data demonstrated foci not only within classical Wernicke's area but also within the middle and inferior frontal gyri. We report the first bilateral probabilistic map for crucial cortical epicentres of human brain functions in the right and left hemispheres, including sensory, motor, and language (speech, articulation, phonology and semantics). These data challenge classical theories of brain organization (e.g. Broca's area as speech output region) and provide a distributed framework for future studies of neural networks.
248 citations
TL;DR: Imprecise consonant articulation was found to be the most powerful indicator of PD-related dysarthria and is envisaged as the first step towards development of acoustic methods allowing the automated assessment of articulatory features in dysarthrias.
Abstract: Although articulatory deficits represent an important manifestation of dysarthria in Parkinson's disease (PD), the most widely used methods currently available for the automatic evaluation of speech performance are focused on the assessment of dysphonia. The aim of the present study was to design a reliable automatic approach for the precise estimation of articulatory deficits in PD. Twenty-four individuals diagnosed with de novo PD and twenty-two age-matched healthy controls were recruited. Each participant performed diadochokinetic tasks based upon the fast repetition of /pa/-/ta/-/ka/ syllables. All phonemes were manually labeled and an algorithm for their automatic detection was designed. Subsequently, 13 features describing six different articulatory aspects of speech including vowel quality, coordination of laryngeal and supralaryngeal activity, precision of consonant articulation, tongue movement, occlusion weakening, and speech timing were analyzed. In addition, a classification experiment using a support vector machine based on articulatory features was proposed to differentiate between PD patients and healthy controls. The proposed detection algorithm reached approximately 80% accuracy for a 5 ms threshold of absolute difference between manually labeled references and automatically detected positions. When compared to controls, PD patients showed impaired articulatory performance in all investigated speech dimensions (p
129 citations
TL;DR: Both clear and loud speech show promise for improving intelligibility and maintaining or improving speech severity in multitalker babble for speakers with mild dysarthria secondary to MS or PD, at least as these perceptual constructs were defined and measured in this study.
Abstract: Purpose The perceptual consequences of rate reduction, increased vocal intensity, and clear speech were studied in speakers with multiple sclerosis (MS), Parkinson's disease (PD), and healthy contr...
129 citations
TL;DR: It is suggested that HKD is a highly complex and variable phenomenon including multiple factors, such as scaling and maintaining movement amplitude and effort; preplanning and initiation of movements; internal cueing; sensory and temporal processing; automaticity; emotive vocalization; and attention to action (vocal vigilance).
Abstract: Purpose Motor speech abnormalities are highly common and debilitating in individuals with idiopathic Parkinson's disease (IPD). These abnormalities, collectively termed hypokinetic dysarthria (HKD), have been traditionally attributed to hypokinesia and bradykinesia secondary to muscle rigidity and dopamine deficits. However, the role of rigidity and dopamine in the development of HKD is far from clear. The purpose of the present study was to offer an alternative view of the factors underlying HKD. Method The authors conducted an extensive, but not exhaustive, review of the literature to examine the evidence for the traditional view versus the alternative view. Results The review suggests that HKD is a highly complex and variable phenomenon including multiple factors, such as scaling and maintaining movement amplitude and effort; preplanning and initiation of movements; internal cueing; sensory and temporal processing; automaticity; emotive vocalization; and attention to action (vocal vigilance). Although ...
126 citations
TL;DR: Vowel metrics derived from spectral and temporal measurements of vowel tokens embedded in phrases produced by 45 speakers with dysarthria and 12 speakers with no history of neurological disease suggest that some vowel metrics may be useful clinically for the detection of dysarthrias but may not be reliable indicators of Dysarthria subtype using the current dysarthia classification scheme.
Abstract: Purpose The purpose of this study was to determine the extent to which vowel metrics are capable of distinguishing healthy from dysarthric speech and among different forms of dysarthria Method A v
112 citations
TL;DR: Speech intelligibility in children with cerebral palsy was evaluated using a prediction model in which acoustic measures were selected to represent three speech subsystems; the articulatory subsystem showed the most substantial independent contribution to speech intelligibility.
Abstract: Purpose Speech acoustic characteristics of children with cerebral palsy (CP) were examined with a multiple speech subsystems approach; speech intelligibility was evaluated using a prediction model in which acoustic measures were selected to represent three speech subsystems. Method Nine acoustic variables reflecting different subsystems, and speech intelligibility, were measured in 22 children with CP. These children included 13 with a clinical diagnosis of dysarthria (speech motor impairment [SMI] group) and 9 judged to be free of dysarthria (no SMI [NSMI] group). Data from children with CP were compared to data from age-matched typically developing children. Results Multiple acoustic variables reflecting the articulatory subsystem were different in the SMI group, compared to the NSMI and typically developing groups. A significant speech intelligibility prediction model was obtained with all variables entered into the model (adjusted R2 = .801). The articulatory subsystem showed the most substantial inde...
89 citations
TL;DR: The most significant predictive factors for deterioration of speech intelligibility when patients were off‐medication/on‐stimulation were lower preoperativespeech intelligibility on‐medicated, longer disease duration, and medially placed left hemisphere active electrode contact.
Abstract: Speech changes after bilateral subthalamic nucleus deep brain stimulation (STN-DBS) can be variable, with the majority of patients experiencing speech deterioration over time. The aim of this study was to describe the perceptual characteristics of speech following chronic STN-DBS and to analyze clinical and surgical factors that could predict speech change. Fifty-four consecutive patients (34 men; mean age ± standard deviation (SD), 58.8 ± 6.3 years; mean ± SD disease duration, 12.5 ± 4.7 years; mean ± SD levodopa equivalent, 1556 ± 671 mg/day; mean ± SD Unified Parkinson's Disease Rating Scale motor part (UPDRS-III) off-medication score, 48.1 ± 17.9 [range, 20-89]; and mean ± SD UPDRS-III on-medication score, 12.4 ± 7.8 [range, 2-31]) participated in this study. They were assessed before and at 1 year after surgery using the Assessment of Intelligibility for the Dysarthric Speech, the perceptual scale from Darley et al., and the UPDRS-III. Speech intelligibility deteriorated on average by 14.4% (P = 0.0006) after 1 year of STN-DBS when off-medication and by 12.3% (P = 0.001) when on-medication. The effect on speech was not linked to age at surgery, unlike the effect on motor outcome. The most significant predictive factors for deterioration of speech intelligibility when patients were off-medication/on-stimulation were lower preoperative speech intelligibility on-medication, longer disease duration, and medially placed left hemisphere active electrode contact. Speech change after STN-DBS is variable and multifactorial. Consistent preoperative speech evaluation would help inform patients about the possible effects of surgery. Appropriate consideration of speech deficits might assist surgical targeting, particularly of the left electrode.
80 citations
TL;DR: This study provides Class IV evidence that in patients with ET treated with DBS with SID, individualized cs-ILS reduces dysarthria while maintaining tremor control and suggests a benefit on SID from individual shaping of current spread while TS is preserved.
Abstract: Objective: To investigate in patients with essential tremor (ET) treated with thalamic/subthalamic deep brain stimulation (DBS) whether stimulation-induced dysarthria (SID) can be diminished by individualized current-shaping with interleaving stimulation (cs-ILS) while maintaining tremor suppression (TS). Methods: Of 26 patients screened, 10 reported SID and were invited for testing. TS was assessed by the Tremor Rating Scale and kinematic analysis of postural and action tremor. SID was assessed by phonetic and logopedic means. Additionally, patients rated their dysarthria on a visual analog scale. Results: In 6 of the 10 patients with ET, DBS-ON (relative to DBS-OFF) led to SID while tremor was successfully reduced. When comparing individualized cs-ILS with a non–current-shaped interleaving stimulation (ILS) in these patients, there was no difference in TS while 4 of the 6 patients showed subjective improvement of speech during cs-ILS. Phonetic analysis (ILS vs cs-ILS) revealed that during cs-ILS there was a reduction of voicing during the production of voiceless stop consonants and also a trend toward an improvement in oral diadochokinetic rate, reflecting less dysarthria. Logopedic rating showed a trend toward deterioration in the diadochokinesis task when comparing ON with OFF but no difference between ILS and cs-ILS. Conclusion: This is a proof-of-principle evaluation of current-shaping in patients with ET treated with thalamic/subthalamic DBS and experiencing SID. Data suggest a benefit on SID from individual shaping of current spread while TS is preserved. Classification of evidence: This study provides Class IV evidence that in patients with ET treated with DBS with SID, individualized cs-ILS reduces dysarthria while maintaining tremor control. Neurology® 2014;82:614–619
79 citations
TL;DR: Three pathomechanisms affecting speech in PD are suggested: diminished energization on the basis of striato-prefrontal hypo-connectivity together with dysfunctional self-monitoring mechanisms, dysarthria may result from fading speech motor representations given that they are not sufficiently well updated by external auditory feedback, and early PD patients show compensatory mechanisms that could help improve future speech therapies.
79 citations
TL;DR: A problem in the clinical assessment of running speech in Parkinson's disease (PD) is to track underlying deficits in a number of speech components including respiration, phonation, articulation and phonation as mentioned in this paper.
76 citations
TL;DR: The present case is the first to involve a single gene within the microdeletion region and a phenotype restricted to a subset of the traits observed in other cases with more extensive deletions, and it is reported on an 11‐year‐old male with a heterozygous de novo 0.2 Mb deletion containing asingle gene, BCL11A.
Abstract: In 10 cases of 2p15p16.1 microdeletions reported worldwide to date, shared phenotypes included growth retardation, craniofacial and skeletal dysmorphic traits, internal organ defects, intellectual disability, nonverbal or low verbal status, abnormal muscle tone, and gross motor delays. The size of the deletions ranged from 0.3 to 5.7 Mb, where the smallest deletion involved the BCL11A, PAPOLG, and REL genes. Here we report on an 11-year-old male with a heterozygous de novo 0.2 Mb deletion containing a single gene, BCL11A, and a phenotype characterized by childhood apraxia of speech and dysarthria in the presence of general oral and gross motor dyspraxia and hypotonia as well as expressive language and mild intellectual delays. BCL11A is situated within the dyslexia susceptibility candidate region 3 (DYX3) candidate region on chromosome 2. The present case is the first to involve a single gene within the microdeletion region and a phenotype restricted to a subset of the traits observed in other cases with more extensive deletions.
TL;DR: Results provide evidence that degraded vowel acoustics have some effect on human perceptual performance, even in the presence of extravowel variables that naturally exert influence in phrase perception.
Abstract: Purpose The aim of the present report was to explore whether vowel metrics, demonstrated to distinguish dysarthric and healthy speech in a companion article (Lansford & Liss, 2014), are able to pre...
TL;DR: This paper studies the application of ANNs as a fixed-length isolated-word SI ASR for individuals who suffer from dysarthria and identifies the best-performing set of MFCC parameters, which can represent dysarthric acoustic features to be used in Artificial Neural Network (ANN)-based ASR.
TL;DR: Clinical features in sporadic nfVPPA caused by FTLD subtypes relate to neurodegeneration of GM and WM in frontal motor speech and language networks and it is proposed that early WM atrophy in nfvPPA is suggestive of FTLD-tau pathology while early selective GM loss might be indicative of FT LD-TDP.
Abstract: Objective: To identify early cognitive and neuroimaging features of sporadic nonfluent/agrammatic variant of primary progressive aphasia (nfvPPA) caused by frontotemporal lobar degeneration (FTLD) subtypes. Methods: We prospectively collected clinical, neuroimaging, and neuropathologic data in 11 patients with sporadic nfvPPA with FTLD-tau (nfvPPA-tau, n = 9) or FTLD–transactive response DNA binding protein pathology of 43 kD type A (nfvPPA-TDP, n = 2). We analyzed patterns of cognitive and gray matter (GM) and white matter (WM) atrophy at presentation in the whole group and in each pathologic subtype separately. We also considered longitudinal clinical data. Results: At first evaluation, regardless of pathologic FTLD subtype, apraxia of speech (AOS) was the most common cognitive feature and atrophy involved the left posterior frontal lobe. Each pathologic subtype showed few distinctive features. At presentation, patients with nfvPPA-tau presented with mild to moderate AOS, mixed dysarthria with prominent hypokinetic features, clear agrammatism, and atrophy in the GM of the left posterior frontal regions and in left frontal WM. While speech and language deficits were prominent early, within 3 years of symptom onset, all patients with nfvPPA-tau developed significant extrapyramidal motor signs. At presentation, patients with nfvPPA-TDP had severe AOS, dysarthria with spastic features, mild agrammatism, and atrophy in left posterior frontal GM only. Selective mutism occurred early, when general neurologic examination only showed mild decrease in finger dexterity in the right hand. Conclusions: Clinical features in sporadic nfvPPA caused by FTLD subtypes relate to neurodegeneration of GM and WM in frontal motor speech and language networks. We propose that early WM atrophy in nfvPPA is suggestive of FTLD-tau pathology while early selective GM loss might be indicative of FTLD-TDP.
TL;DR: The results of this study suggested that children with mild motor speech impairments are more likely to demonstrate superior activity and participation outcomes compared to children with moderate or severe deficits.
Abstract: The present study used a population-based sample of children with cerebral palsy (CP) to estimate the prevalence of motor speech impairment and its association with activity and participation. A sample of 79 Victorian children aged 4 years 11 months to 6 years 5 months was recruited through the Victorian CP Register. The presence of motor speech impairment was recorded using the Viking Speech Scale (VSS). Activity and participation outcomes included speech intelligibility (the National Technical Institute for the Deaf rating scale, NTID), the Functional Communication Classification System (FCCS) and Communication Function Classification System (CFCS). A parent completed rating scale was used to examine the association between motor speech impairment and participation. Ninety per cent (71/79) of children demonstrated a motor speech impairment. Strong associations were found between the VSS and NTID (< .001), CFCS (< .001), and FCCS levels (<.001). VSS levels III-IV were significantly associated with restrictions in home, school, and community-based participation as perceived by parents. Although some diversity in activity and participation outcomes was observed within specific VSS levels, the results of this study suggested that children with mild motor speech impairments are more likely to demonstrate superior activity and participation outcomes compared to children with moderate or severe deficits.
TL;DR: In a population representative group of YP, aged 16-18 years, with bilateral CP, 63% had impaired speech of varying severity, most had been provided with AAC but few used it at home for communication.
Abstract: BACKGROUND: Communication is frequently impaired in young people (YP) with bilateral cerebral palsy (CP). Important factors include motoric speech problems (dysarthria) and intellectual disability. Augmentative and Alternative Communication (AAC) techniques are often employed. The aim was to describe the speech problems in bilateral CP, factors associated with speech problems, current AAC provision and use, and to explore the views of both the parent/carer and young person about communication. METHODS: A total population of children with bilateral CP (n = 346) from four consecutive years of births (1989-1992 inclusive) with onset of CP before 15 months were reassessed at age 16-18 years. Motor skills and speech were directly assessed and both parent/carer and the young person asked about communication and satisfaction with it. RESULTS: Sixty had died, eight had other conditions, 243 consented and speech was assessed in 224 of whom 141 (63%) had impaired speech. Fifty-two (23% of total YP) were mainly intelligible to unfamiliar people, 22 (10%) were mostly unintelligible to unfamiliar people, 67 (30%) were mostly or wholly unintelligible even to familiar adults. However, 89% of parent/carers said that they could communicate 1:1 with their young person. Of the 128 YP who could independently complete the questions, 107 (83.6%) were happy with their communication, nine (7%) neither happy nor unhappy and 12 (9.4%) unhappy. A total of 72 of 224 (32%) were provided with one or more types of AAC but in a significant number (75% of 52 recorded) AAC was not used at home, only in school. Factors associated with speech impairment were severity of physical impairment, as measured by Gross Motor Function Scale level and manipulation in the best hand, intellectual disability and current epilepsy. CONCLUSIONS: In a population representative group of YP, aged 16-18 years, with bilateral CP, 63% had impaired speech of varying severity, most had been provided with AAC but few used it at home for communication.
TL;DR: Results suggest that reducing both the length and phonetic complexity of utterances may enhance intelligibility for children with dysarthria, however, there may be important individual differences in the impact of one or both types of sentence characteristics.
Abstract: Reduced speech intelligibility is a barrier to effective communication for many children with cerebral palsy (CP). Many variables may impact intelligibility, yet little research attention has sought to quantify these variables. This study examined the influence of sentence characteristics on intelligibility in two groups of children with CP (those with and without dysarthria) and typically-developing children. Questions addressed effects of sentence length on transcription intelligibility among groups; effects of phonetic complexity on intelligibility; and differences in the relationship between sentence characteristics and intelligibility across individual children with dysarthria. Speech samples varying in length from 2-7 words were elicited from 16 children with CP (mean age 59.6 months) and eight typically-developing children (mean age = 59.8 months). One hundred and nineteen naive listeners made orthographic transcriptions of the children's sentence productions. Sentence length and phonetic complexity affected intelligibility for all groups of children, but had a greater impact on intelligibility for children with dysarthria than those without speech motor impairment. Variable relationships between sentence characteristics and intelligibility were found across individual children with dysarthria. Results suggest that reducing both the length and phonetic complexity of utterances may enhance intelligibility for children with dysarthria. However, there may be important individual differences in the impact of one or both types of sentence characteristics. This highlights the importance of considering individual speech motor profiles when deciding on treatment strategies.
TL;DR: Investigation of the speech characteristics of school-aged children with cerebral palsy and speech impairment at various cognitive levels found gross motor problems were not significantly associated with the articulation of consonants or the severity of dysarthria, whereas non-verbal cognitive level was.
Abstract: The aim of the present study was to investigate the speech characteristics of school-aged children with cerebral palsy (CP) and speech impairment at various cognitive levels. Nineteen children with a mean age of 11;2 years (9;2-12;9 years) with spastic, dyskinetic, and ataxic CP and speech impairment participated. Phonetic transcription of oral consonants, ratings of hypernasality, and severity of overall dysarthria, together with free field descriptions of respiration, voice quality, and prosody, were performed independently by two speech-language pathologists. The non-verbal cognitive level was also studied. More than half of the children had large problems with the articulation of consonants, and the children with ataxic CP were most affected. The majority was rated as having dysarthria, mostly mild, but hypernasality was rare. Gross motor problems were not significantly associated with the articulation of consonants or the severity of dysarthria, whereas non-verbal cognitive level was. This underlines the importance of taking non-verbal cognitive level into account, when designing individual speech treatment programs for this group of children. Finally, a careful examination of the articulation of consonants is recommended in order to study speech production thoroughly in children with CP.
TL;DR: The influence of subthalamic StimON Parkinsonian speech differs considerably between individual patients, however, there is a trend to amelioration of voice quality and prosody.
Abstract: Background: Deep brain stimulation of the subthalamic nucleus, although highly effective for the treatment of motor impairment in Parkinson´s disease, can induce speech deterioration in a subgroup of patients. The aim of the current study was to survey 1) if there are distinctive stimulation effects on the different parameters of voice and speech and 2) if there is a special pattern of preexisting speech abnormalities indicating a risk for further worsening under stimulation. Methods: N = 38 patients with Parkinson´s disease had to perform a speech test without medication with stimulation ON and OFF. Speech samples were analysed: 1) according to a four-dimensional perceptual speech score and 2) by acoustic analysis to obtain quantifiable measures of distinctive speech parameters.Results: Quality of voice was ameliorated with stimulation ON, and there were trends to increased loudness and better pitch variability. N = 8 patients featured a deterioration of speech with stimulation ON, caused by worsening of articulation or/and fluency. These patients had more severe overall speech impairment with characteristic features of articulatory slurring and articulatory acceleration already under StimOFF condition.Conclusion: The influence of subthalamic stimulation on Parkinsonian speech differs considerably between individual patients, however, there is a trend to amelioration of voice quality and prosody. Patients with stimulation-associated speech deterioration featured higher overall speech impairment and showed a distinctive pattern of articulatory abnormalities at baseline. Further investigations to confirm these preliminary findings are necessary to allow neurologists to pre-surgically estimate the individual risk of deterioration of speech under stimulation.
TL;DR: It is demonstrated that listeners can judge how well they have understood dysarthria and cerebral palsy speech, and EOL is associated with listener familiarity, speech task and speech impairment severity.
Abstract: Purpose: This study aimed to investigate the association between listeners’ ratings of how much effort it took to understand the speech of young people with cerebral palsy and the percentage of words listeners actually understood.Method: Thirty-one young people with dysarthria and cerebral palsy (16 males, 15 females; mean age = 11 years, SD = 3) were audio recorded repeating single words and producing speech. Objective measures of intelligibility were calculated for multiple familiar and unfamiliar listeners using a forced choice paradigm for single words and verbatim orthographic transcriptions for connected speech. Listeners rated how much effort it took to understand speech in each condition using a 5-point ordinal ease of listening (EOL) scale.Results: Agreement on EOL within rater groups was high (ICC > 0.71). An effect of listener was observed for familiar listeners, but not for unfamiliar listeners. EOL agreement between familiar and unfamiliar listeners was weak–moderate (ICC = 0.46). EOL...
TL;DR: Speech rate related to connected speech and parameters of syllable repetition showed correlations to overall motor impairment, capacity of tapping in a quantitative motor assessment and some score of cognitive function.
Abstract: Dysarthria is a common symptom of Huntington's disease and has been reported, besides other features, to be characterized by alterations of speech rate and regularity. However, data on the specific pattern of motor speech impairment and their relationship to other motor and neuropsychological symptoms are sparse. Therefore, the aim of the present study was to describe and objectively analyse different speech parameters with special emphasis on the aspect of speech timing of connected speech and non-speech verbal utterances. 21 patients with manifest Huntington's disease and 21 age- and gender-matched healthy controls had to perform a reading task and several syllable repetition tasks. Computerized acoustic analysis of different variables for the measurement of speech rate and regularity generated a typical pattern of impaired motor speech performance with a reduction of speech rate, an increase of pauses and a marked disability to steadily repeat single syllables. Abnormalities of speech parameters were more pronounced in the subgroup of patients with Huntington's disease receiving antidopaminergic medication, but were also present in the drug-naive patients. Speech rate related to connected speech and parameters of syllable repetition showed correlations to overall motor impairment, capacity of tapping in a quantitative motor assessment and some score of cognitive function. After these preliminary data, further investigations on patients in different stages of disease are warranted to survey if the analysis of speech and non-speech verbal utterances might be a helpful additional tool for the monitoring of functional disability in Huntington's disease.
TL;DR: The results show that the speech acoustic models derived from suitable adaptation techniques improve the performance of ASR systems in recognising impaired speech with limited adaptation data.
Abstract: Automatic speech recognition (ASR) is currently used in many assistive technologies, such as helping individuals with speech impairment in their communication ability. One challenge in ASR for speech-impaired individuals is the difficulty in obtaining a good speech database of impaired speakers for building an effective speech acoustic model. Because there are very few existing databases of impaired speech, which are also limited in size, the obvious solution to build a speech acoustic model of impaired speech is by employing adaptation techniques. However, issues that have not been addressed in existing studies in the area of adaptation for speech impairment are as follows: (1) identifying the most effective adaptation technique for impaired speech; and (2) the use of suitable source models to build an effective impaired-speech acoustic model. This research investigates the above-mentioned two issues on dysarthria, a type of speech impairment affecting millions of people. We applied both unimpaired and impaired speech as the source model with well-known adaptation techniques like the maximum likelihood linear regression (MLLR) and the constrained-MLLR(C-MLLR). The recognition accuracy of each impaired speech acoustic model is measured in terms of word error rate (WER), with further assessments, including phoneme insertion, substitution and deletion rates. Unimpaired speech when combined with limited high-quality speech-impaired data improves performance of ASR systems in recognising severely impaired dysarthric speech. The C-MLLR adaptation technique was also found to be better than MLLR in recognising mildly and moderately impaired speech based on the statistical analysis of the WER. It was found that phoneme substitution was the biggest contributing factor in WER in dysarthric speech for all levels of severity. The results show that the speech acoustic models derived from suitable adaptation techniques improve the performance of ASR systems in recognising impaired speech with limited adaptation data.
11 Mar 2014
TL;DR: A Dysarthric multi-networks speech recognizer (DM-NSR) model is provided using a realization of multi-views multi-learners approach called multi-nets artificial neural networks, which tolerates variability of dysarthric speech.
Abstract: Automatic speech recognition (ASR) can be very helpful for speakers who suffer from dysarthria, a neurological disability that damages the control of motor speech articulators. Although a few attempts have been made to apply ASR technologies to sufferers of dysarthria, previous studies show that such ASR systems have not attained an adequate level of performance. In this study, a dysarthric multi-networks speech recognizer (DM-NSR) model is provided using a realization of multi-views multi-learners approach called multi-nets artificial neural networks, which tolerates variability of dysarthric speech. In particular, the DM-NSR model employs several ANNs (as learners) to approximate the likelihood of ASR vocabulary words and to deal with the complexity of dysarthric speech. The proposed DM-NSR approach was presented as both speaker-dependent and speaker-independent paradigms. In order to highlight the performance of the proposed model over legacy models, multi-views single-learner models of the DM-NSRs were also provided and their efficiencies were compared in detail. Moreover, a comparison among the prominent dysarthric ASR methods and the proposed one is provided. The results show that the DM-NSR recorded improved recognition rate by up to 24.67% and the error rate was reduced by up to 8.63% over the reference model.
TL;DR: Examination of the response patterns indicated that intensity is necessary but not sufficient for change, and possibilities are presented for technological solutions designed to promote accessibility to the intensive task repetition and maintenance required to drive lasting changes.
Abstract: This study describes the use of a neuroplasticity-principled speech treatment approach (LSVT(®)LOUD) with children who have dysarthria secondary to cerebral palsy. To date, the authors have treated 25 children with mild-to-severe dysarthria, a continuum of gross and fine motor functions, and variable cognitive abilities. From this data set, two case studies are presented that represent as weak or strong responders to LSVT LOUD. These case studies demonstrate how individual and environmental features may impact immediate and lasting responses to treatment. Principles that drive activity-dependent neuroplasticity are embedded in LSVT LOUD and may contribute to positive therapeutic and acoustic outcomes. However, examination of the response patterns indicated that intensity (within and across treatment sessions) is necessary but not sufficient for change. Weak responders may require a longer treatment phase, better timing (e.g., developmentally, socially), and a more prominent desire to communicate successfully during daily activities. Strong responders appear to benefit from the intensity and saliency of treatment as well as from intrinsic and extrinsic rewards for using the trained skills for everyday communication. Finally, possibilities are presented for technological solutions designed to promote accessibility to the intensive task repetition and maintenance required to drive lasting changes.
TL;DR: Positive outcomes indicate positive outcomes associated with a short period of behavioural SLT intervention in the post-stroke dysarthria population.
Abstract: Methods & Procedures: Thirty-nine participants were randomized into Group A (n = 20) and Group B (n = 19). Groups were equivalent at enrolment in demographic variables and A1 measures. Intervention was behavioural, delivered in eight home-based SLT sessions, and included practise of individually appropriate words, sentences and conversation, and for Group B also NSOMExs. Between-session practice was recorded in a diary. Data on speech intelligibility, effectiveness of communication in conversation, self-rated situational communication effectiveness, and tongue and lip movement were collected at 8-week intervals, twice before and twice after intervention. Anonymous evaluation (AE) questionnaires were completed. Outcome & Results The recruited number was 20% below the target of 50. Thirty-six participants completed the intervention and 32 were followed through to A4. The programme was delivered to protocol and fidelity was verified. Thirty-four AEs were returned. These showed high satisfaction with the programme and its outcome. According to diary records from 32 participants, 59% carried out at least the recommended practice amount. Outcome measure performance across the four assessment points did not indicate any group effect. For the whole sample both externally rated and self-rated communication effectiveness measures showed statistically significant gains across the intervention period (A2/A3), which were maintained for 2 months after intervention (A2/A4). Non-intervention period changes (A1/A2 and A3/A4) were not present. There were no intervention-related gains in tongue and lip movement or speech intelligibility, but the latter is likely to be attributable to a ceiling effect on scores. Background: There has been little robust evaluation of the outcome of speech and language therapy (SLT) intervention for post-stroke dysarthria. Non-speech oro-motor exercises (NSOMExs) are a common component of dysarthria intervention. A feasibility study was designed and executed, with participants randomized into two groups, in one of which NSOMExs were a component of the intervention programme. Aims: To examine (1) operational feasibility of the programme; (2) participants' views of the programme; and (3) speech intelligibility, communication effectiveness and tongue and lip movement at four points (A1 and A2 before, and A3 and A4 after intervention). Conclusions & Implications: The results indicate positive outcomes associated with a short period of behavioural SLT intervention in the post-stroke dysarthria population. The inclusion of NSOMExs, delivered in accordance with standard clinical practice, did not appear to influence outcomes. The results must be viewed in relation to the nature of feasibility study and provide a foundation for suitably powered trials.
TL;DR: The results support the construct-related validity of TOCS as a tool for obtaining intelligibility and rate scores that are sensitive to group differences in 3-6 year- old children, with and without speech sound disorders, and to 3+ year-old children with speech disorders,With and without dysarthria.
TL;DR: This paper presents an approach that integrates multiple pronunciation patterns for enhancement of dysarthric speech recognition by weighting the responses of an Automatic Speech Recognition (ASR) system when different language model restrictions are set.
Abstract: Dysarthria is a motor speech disorder caused by neurological injury of the motor component of the motor-speech system. Because it affects respiration, phonation, and articulation, it leads to different types of impairments in intelligibility, audibility, and efficiency of vocal communication. Speech Assistive Technology (SAT) has been developed with different approaches for dysarthric speech and in this paper we focus on the approach that is based on modeling of pronunciation patterns. We present an approach that integrates multiple pronunciation patterns for enhancement of dysarthric speech recognition. This integration is performed by weighting the responses of an Automatic Speech Recognition (ASR) system when different language model restrictions are set. The weight for each response is estimated by a Genetic Algorithm (GA) that also optimizes the structure of the implementation technique (Metamodels) which is based on discrete Hidden Markov Models (HMMs). The GA makes use of dynamic uniform mutation/crossover to further diversify the candidate sets of weights and structures to improve the performance of the Metamodels. To test the approach with a larger vocabulary than in previous works, we orthographically and phonetically labeled extended acoustic resources from the Nemours database of dysarthric speech. ASR tests on these resources with the proposed approach showed recognition accuracies over those obtained with standard Metamodels and a well used speaker adaptation technique. These results were statistically significant.
TL;DR: Dysarthria-related QOL is compromised in patients with MS and dysarthria and might be used as a supplementary measure in clinical practice and research for patients who have MS.
TL;DR: Results suggest that diversity among speakers with PD should be considered when interpreting results from group analyses, and articulatory rate, fundamental frequency and F2 IQR were most frequently associated with within-speaker variation in sentence intelligibility.
Abstract: This study investigated the acoustic basis of within-speaker, across-utterance variation in sentence intelligibility for 12 speakers with dysarthria secondary to Parkinson’s disease (PD). Acoustic measures were also obtained for 12 healthy controls for comparison to speakers with PD. Speakers read sentences using their typical speech style. Acoustic measures of speech rate, articulatory rate, fundamental frequency, sound pressure level and F2 interquartile range (F2 IQR) were obtained. A group of listeners judged sentence intelligibility using a computerized visual-analog scale. Relationships between judgments of intelligibility and acoustic measures were determined for individual speakers with PD. Relationships among acoustic measures were also quantified. Although considerable variability was noted, articulatory rate, fundamental frequency and F2 IQR were most frequently associated with within-speaker variation in sentence intelligibility. Results suggest that diversity among speakers with PD sh...
29 Sep 2014
TL;DR: The National Institutes of Health Stroke Scale (NIHSS) is a systematic assessment tool designed to measure the neurological deficits most often seen with acute stroke.
Abstract: The National Institutes of Health Stroke Scale (NIHSS) is a systematic assessment tool designed to measure the neurological deficits most often seen with acute stroke. It assesses level of consciousness, gaze, visual fields, facial weakness, motor performance of the extremities, sensory deficit, coordination (ataxia), language (aphasia), speech (dysarthria), and hemi-inattention (neglect). For all parameters, a value of 0 is normal; so, the higher the score, the worse the neurological deficit (the highest possible score is 42). The scale was designed to be done quickly and easily at the bedside to provide a rapid and standardized assessment of neurological function in the early periods after a stroke. It has been validated and has been shown to be reliable, even when performed by non-neurologists and non-physicians.
Keywords:
stroke scales;
neurological deficit scales;
NIHSS ;
clinimetrics