-
IEEE Transactions on Neural Systems and... 2023Dysarthria, a speech disorder often caused by neurological damage, compromises the control of vocal muscles in patients, making their speech unclear and communication...
Dysarthria, a speech disorder often caused by neurological damage, compromises the control of vocal muscles in patients, making their speech unclear and communication troublesome. Recently, voice-driven methods have been proposed to improve the speech intelligibility of patients with dysarthria. However, most methods require a significant representation of both the patient's and target speaker's corpus, which is problematic. This study aims to propose a data augmentation-based voice conversion (VC) system to reduce the recording burden on the speaker. We propose dysarthria voice conversion 3.1 (DVC 3.1) based on a data augmentation approach, including text-to-speech and StarGAN-VC architecture, to synthesize a large target and patient-like corpus to lower the burden of recording. An objective evaluation metric of the Google automatic speech recognition (Google ASR) system and a listening test were used to demonstrate the speech intelligibility benefits of DVC 3.1 under free-talk conditions. The DVC system without data augmentation (DVC 3.0) was used for comparison. Subjective and objective evaluation based on the experimental results indicated that the proposed DVC 3.1 system enhanced the Google ASR of two dysarthria patients by approximately [62.4%, 43.3%] and [55.9%, 57.3%] compared to unprocessed dysarthria speech and the DVC 3.0 system, respectively. Further, the proposed DVC 3.1 increased the speech intelligibility of two dysarthria patients by approximately [54.2%, 22.3%] and [63.4%, 70.1%] compared to unprocessed dysarthria speech and the DVC 3.0 system, respectively. The proposed DVC 3.1 system offers significant potential to improve the speech intelligibility performance of patients with dysarthria and enhance verbal communication quality.
Topics: Humans; Dysarthria; Voice; Speech Intelligibility; Laryngeal Muscles
PubMed: 37938964
DOI: 10.1109/TNSRE.2023.3331524 -
Brain : a Journal of Neurology Apr 2024Mitochondrial membrane protein-associated neurodegeneration (MPAN) is an ultraorphan neurogenetic disease from the group of neurodegeneration with brain iron...
Mitochondrial membrane protein-associated neurodegeneration (MPAN) is an ultraorphan neurogenetic disease from the group of neurodegeneration with brain iron accumulation (NBIA) disorders. Here we report cross-sectional and longitudinal data to define the phenotype, to assess disease progression and to estimate sample sizes for clinical trials. We enrolled patients with genetically confirmed MPAN from the Treat Iron-Related Childhood-Onset Neurodegeneration (TIRCON) registry and cohort study, and from additional sites. Linear mixed-effect modelling (LMEM) was used to calculate annual progression rates for the Unified Parkinson's Disease Rating Scale (UPDRS), Barry-Albright Dystonia (BAD) scale, Schwab and England Activities of Daily Living (SE-ADL) scale and the Pediatric Quality of Life Inventory (PedsQL). We investigated 85 MPAN patients cross-sectionally, with functional outcome data collected in 45. Median age at onset was 9 years and the median diagnostic delay was 5 years. The most common findings were gait disturbance (99%), pyramidal involvement (95%), dysarthria (90%), vision disturbances (82%), with all but dysarthria presenting early in the disease course. After 16 years with the disease, 50% of patients were wheelchair dependent. LMEM showed an annual progression rate of 4.5 points in total UPDRS. The total BAD scale score showed no significant progression over time. The SE-ADL scale and the patient- and parent-reported PedsQL showed a decline of 3.9%, 2.14 and 2.05 points, respectively. No patient subpopulations were identified based on longitudinal trajectories. Our cross-sectional results define the order of onset and frequency of symptoms in MPAN, which will inform the diagnostic process, help to shorten diagnostic delay and aid in counselling patients, parents and caregivers. Our longitudinal findings define the natural history of MPAN, reveal the most responsive outcomes and highlight the need for an MPAN-specific rating approach. Our sample size estimations inform the design of upcoming clinical trials.
Topics: Child; Humans; Dysarthria; Cohort Studies; Activities of Daily Living; Cross-Sectional Studies; Delayed Diagnosis; Quality of Life; Mutation; Neurodegenerative Diseases; Phenotype; Dystonia; Dystonic Disorders; Membrane Proteins; Mitochondrial Membranes
PubMed: 37831662
DOI: 10.1093/brain/awad357 -
Folia Phoniatrica Et Logopaedica :... 2021The use of commercially available automatic speech recognition (ASR) software is challenged when dysarthria accompanies a physical disability. To overcome this issue, a...
INTRODUCTION
The use of commercially available automatic speech recognition (ASR) software is challenged when dysarthria accompanies a physical disability. To overcome this issue, a mobile and personal speech assistant (mPASS) platform was developed, using a speaker-dependent ASR software.
OBJECTIVE
The aim of this study was to evaluate the performance of the proposed platform and to compare mPASS recognition accuracy to a commercial speaker-independent ASR software. In addition, secondary aims were to investigate the relationship between severity of dysarthria and accuracy and to explore people with dysarthria perceptions on the proposed platform.
METHODS
Fifteen individuals with dysarthric speech and 20 individuals with nondysarthric speech recorded 24 words and 5 sentences in a clinical environment. Differences in recognition accuracy between the two systems were evaluated. In addition, mPASS usability was assessed with a technology acceptance model (TAM) questionnaire.
RESULTS
In both groups, mean accuracy rates were significantly higher with mPASS compared to the commercial ASR for words and for sentences. mPASS reached good levels of usefulness and ease of use according to the TAM questionnaire.
CONCLUSIONS
Practical applicability of this technology is realistic: the mPASS platform is accurate, and it could be easily used by individuals with dysarthria.
Topics: Dysarthria; Humans; Speech; Speech Intelligibility; Speech Perception; Speech Production Measurement; Speech Recognition Software
PubMed: 33190131
DOI: 10.1159/000511042 -
American Journal of Speech-language... Mar 2021Purpose COVID-19 has shifted models of health care delivery, requiring the rapid adoption of telehealth, despite limited evidence and few resources to guide... (Review)
Review
Purpose COVID-19 has shifted models of health care delivery, requiring the rapid adoption of telehealth, despite limited evidence and few resources to guide speech-language pathologists. Management of dysarthria presents specific challenges in the telehealth modality. Evaluations of dysarthria typically rely heavily on perceptual judgments, which are difficult to obtain via telehealth given a variety of technological factors such as inconsistencies in mouth-to-microphone distance, changes to acoustic properties based on device settings, and possible interruptions in connection that may cause video freezing. These factors limit the validity, reliability, and clinicians' certainty of perceptual speech ratings via telehealth. Thus, objective measures to supplement the assessment of dysarthria are essential. Method This tutorial outlines how to obtain objective measures in real time and from recordings of motor speech evaluations to support traditional perceptual ratings in telehealth evaluations of dysarthria. Objective measures include pause patterns, utterance length, speech rate, diadochokinetic rates, and overall speech severity. We demonstrate, through clinical case vignettes, how these measures were completed following three clinical telehealth evaluations of dysarthria conducted via Zoom during the COVID-19 pandemic. This tutorial describes how each of these objective measures were utilized, in combination with subjective perceptual analysis, to determine deviant speech characteristics and their etiology, develop a patient-specific treatment plan, and track change over time. Conclusion Utilizing objective measures as an adjunct to perceptual ratings for telehealth dysarthria evaluations is feasible under real-world pandemic conditions and can be used to enhance the quality and utility of these evaluations.
Topics: COVID-19; Dysarthria; Humans; Pandemics; SARS-CoV-2; Speech Intelligibility; Speech-Language Pathology; Telemedicine
PubMed: 33689471
DOI: 10.1044/2020_AJSLP-20-00243 -
Journal of Speech, Language, and... Aug 2023Although articulatory impairment represents distinct speech characteristics in most neurological diseases affecting movement, methods allowing automated assessments of...
PURPOSE
Although articulatory impairment represents distinct speech characteristics in most neurological diseases affecting movement, methods allowing automated assessments of articulation deficits from the connected speech are scarce. This study aimed to design a fully automated method for analyzing dysarthria-related vowel articulation impairment and estimate its sensitivity in a broad range of neurological diseases and various types and severities of dysarthria.
METHOD
Unconstrained monologue and reading passages were acquired from 459 speakers, including 306 healthy controls and 153 neurological patients. The algorithm utilized a formant tracker in combination with a phoneme recognizer and subsequent signal processing analysis.
RESULTS
Articulatory undershoot of vowels was presented in a broad spectrum of progressive neurodegenerative diseases, including Parkinson's disease, progressive supranuclear palsy, multiple-system atrophy, Huntington's disease, essential tremor, cerebellar ataxia, multiple sclerosis, and amyotrophic lateral sclerosis, as well as in related dysarthria subtypes including hypokinetic, hyperkinetic, ataxic, spastic, flaccid, and their mixed variants. Formant ratios showed a higher sensitivity to vowel deficits than vowel space area. First formants of corner vowels were significantly lower for multiple-system atrophy than cerebellar ataxia. Second formants of vowels /a/ and /i/ were lower in ataxic compared to spastic dysarthria. Discriminant analysis showed a classification score of up to 41.0% for disease type, 39.3% for dysarthria type, and 49.2% for dysarthria severity. Algorithm accuracy reached an F-score of 0.77.
CONCLUSIONS
Distinctive vowel articulation alterations reflect underlying pathophysiology in neurological diseases. Objective acoustic analysis of vowel articulation has the potential to provide a universal method to screen motor speech disorders.
SUPPLEMENTAL MATERIAL
https://doi.org/10.23641/asha.23681529.
Topics: Humans; Dysarthria; Speech; Cerebellar Ataxia; Parkinson Disease; Articulation Disorders; Atrophy; Speech Acoustics; Speech Intelligibility
PubMed: 37499137
DOI: 10.1044/2023_JSLHR-22-00526 -
Disability and Rehabilitation.... Oct 2023More than 80% of people living with Amyotrophic Lateral Sclerosis (plwALS) develop difficulties with their speech, affecting communication, self-identity and quality of... (Review)
Review
BACKGROUND
More than 80% of people living with Amyotrophic Lateral Sclerosis (plwALS) develop difficulties with their speech, affecting communication, self-identity and quality of life. Automatic speech recognition technology (ASR) is becoming a common way to interact with a broad range of devices, to find information and control the environment.ASR can be problematic for people with acquired neurogenic motor speech difficulties (dysarthria). Given that the field is rapidly developing, a scoping review is warranted.
AIMS
This study undertakes a scoping review on the use of ASR technology by plwALS and identifies research gaps in the existing literature.
MATERIALS AND METHODS
Electronic databases and relevant grey literature were searched from 1990 to 2020. Eleven research papers and articles were identified that included participants living with ALS using ASR technology. Relevant data were extracted from the included sources, and a narrative summary of the findings presented. Eleven publications used recordings of plwALS to assess word recognition rate (WRR) word error rate (WER) or phoneme error rate (PER) and appropriacy of responses by ASR devices. All were found to be linked to severity of dysarthria and the ASR technology used. One article examined how speech modification may improve ASR accuracy. The final article completed thematic analysis of Amazon.com reviews for the Amazon Echo and plwALS were reported to use ASR devices to control the environment and summon assistance.
CONCLUSIONS
There are gaps in the evidence base: understanding expectations of plwALS and how they use ASR technology; how WER/PER/WRR relates to usability; how ASR use changes as ALS progresses.Implications for rehabilitationDevices that people can interact with using speech are becoming ubiquitous. As movement and mobility are likely to be affected by ALS and progress over time, speech interaction could be very helpful for accessing information and environmental control.However, many people living with ALS (plwALS) also have impaired speech (dysarthria) and experience trouble using voice interaction technology because it may not understand them.Although advances in automated speech recognition (ASR) technology promise better understanding of dysarthric speech, future research needs to investigate how plwALS use ASR, how accurate it needs to be to be functionally useful, and how useful it may be over time as the disease progresses.
Topics: Humans; Speech; Dysarthria; Amyotrophic Lateral Sclerosis; Speech Perception; Speech Recognition Software; Quality of Life; Speech Disorders
PubMed: 34511007
DOI: 10.1080/17483107.2021.1974961 -
American Journal of Speech-language... Aug 2023Few studies have reported on the vowel space area (VSA) in both acoustic and kinematic domains. This study examined acoustic and kinematic VSAs for speakers with and...
PURPOSE
Few studies have reported on the vowel space area (VSA) in both acoustic and kinematic domains. This study examined acoustic and kinematic VSAs for speakers with and without dysarthria and evaluated effects of normalization on acoustic and kinematic VSAs and the relationship between these measures.
METHOD
Vowel data from 12 speakers with and without dysarthria, presenting with a range of speech abilities, were examined. The speakers included four speakers with Parkinson's disease (PD), four speakers with brain injury (BI), and four neurotypical (NT) speakers. Speech acoustic and kinematic data were acquired simultaneously using electromagnetic articulography during a passage reading task. Raw and normalized VSAs calculated from corner vowels /i/, /æ/, /ɑ/, and /u/ were evaluated. Normalization was achieved through score transformations to the acoustic and kinematic data. The effect of normalization on variability within and across groups was evaluated. Regression analysis was used across speakers to assess the association between acoustic and kinematic VSAs for both raw and normalized data.
RESULTS
When evaluating the speakers as three different groups (i.e., PD, BI, and NT), normalization reduced the standard deviations within each group and changed the relative differences in average magnitude between groups. Regression analysis revealed a significant relationship between normalized, but not raw, acoustic and kinematic VSAs, after the exclusion of an outlier speaker.
CONCLUSIONS
Normalization reduces the variability across speakers, within groups, and changes average magnitudes affecting speaker group comparisons. Normalization also influences the correlation between acoustic and kinematic measures. Further investigation of the impact of normalization techniques upon acoustic and kinematic measures is warranted.
SUPPLEMENTAL MATERIAL
https://doi.org/10.23641/asha.22669747.
Topics: Humans; Speech Intelligibility; Speech Production Measurement; Speech Acoustics; Dysarthria; Biomechanical Phenomena; Acoustics; Parkinson Disease; Phonetics
PubMed: 37105919
DOI: 10.1044/2023_AJSLP-22-00158 -
Logopedics, Phoniatrics, Vocology Apr 2022Myasthenia Gravis (MG) is an autoimmune disease. The characteristic symptoms of the disease are muscle weakness and fatigue. These symptoms affect de oral muscles...
INTRODUCTION
Myasthenia Gravis (MG) is an autoimmune disease. The characteristic symptoms of the disease are muscle weakness and fatigue. These symptoms affect de oral muscles causing dysarthria, affecting about 60% of patients with disease progression.
PURPOSE
Describe the speech pattern of patients with MG and comparing with healthy controls (HC).
MATERIAL AND METHODS
Case-control study. Participants were divided in MG group (MGG) with 38 patients MG diagnosed and HC with 18 individuals matched for age and sex. MGG was evaluated with clinical and motor scales and answered self-perceived questionnaires. Speech assessment of both groups included: recording of speech tasks, acoustic and auditory-perceptual analysis.
RESULTS
In the MGG, 68.24% of the patients were female, with average age of 50.21 years old (±16.47), 14.18 years (±9.52) of disease duration and a motor scale of 11.19 points (±8.79). The auditory-perceptual analysis verified that 47.36% ( = 18) participants in MGG presented mild dysarthria, 10.52% ( = 4) moderate dysarthria, with a high percentage of alterations in phonation (95.2%) and breathing (52.63%). The acoustic analysis verified a change in phonation, with significantly higher shimmer values in the MGG compared to the HC and articulation with a significant difference between the groups for the first formant of the /iu/ ( = <.001). No correlation was found between the diagnosis of speech disorder and the dysarthria self-perception questionnaire.
CONCLUSION
We found dysarthria mild in MG patients with changes in the motor bases phonation and breathing, with no correlation with severity and disease duration.
Topics: Case-Control Studies; Dysarthria; Female; Humans; Male; Middle Aged; Myasthenia Gravis; Speech; Speech Acoustics; Voice Quality
PubMed: 33106062
DOI: 10.1080/14015439.2020.1834614 -
Journal of Speech, Language, and... Aug 2021Purpose Early studies of perceptual learning of dysarthric speech, those summarized in Borrie, McAuliffe, and Liss (2012), yielded preliminary evidence that listeners... (Review)
Review
Purpose Early studies of perceptual learning of dysarthric speech, those summarized in Borrie, McAuliffe, and Liss (2012), yielded preliminary evidence that listeners could to better understand the speech of a person with dysarthria, revealing a potentially promising avenue for future intelligibility interventions. Since then, a programmatic body of research grounded in models of perceptual processing has unfolded. The current review provides an updated account of the state of the evidence in this area and offers direction for moving this work toward clinical implementation. Method The studies that have investigated perceptual learning of dysarthric speech ( = 24) are summarized and synthesized first according to the proposed learning source and then by highlighting the parameters that appear to mediate learning, culminating with additional learning outcomes. Results The recent literature has established strong empirical evidence of intelligibility improvements following familiarization with dysarthric speech and a theoretical account of the mechanisms that facilitate improved processing of the neurologically degraded acoustic signal. Conclusions There are no existing intelligibility interventions for individuals with dysarthria who cannot behaviorally modify their speech. However, there is now robust support for the development of an approach that shifts the weight of behavioral change from speaker to listener, exploiting perceptual learning to ease the intelligibility burden of dysarthria. To move this work from bench to bedside, recommendations for translational studies that establish best practices and candidacy for listener-targeted dysarthria remediation, perceptual training, are provided.
Topics: Cognition; Dysarthria; Humans; Learning; Speech Intelligibility; Speech Perception; Speech Production Measurement
PubMed: 34289312
DOI: 10.1044/2021_JSLHR-21-00012 -
Disability and Rehabilitation.... Oct 2023The fragmented nature of the medical device market limits our understanding of how particular sub-markets navigate the device development process. Despite the widespread... (Review)
Review
Mapping the development process of transcutaneous neuromuscular electrical stimulation devices for neurorehabilitation, the associated barriers and facilitators, and its applicability to acquired dysarthria: a qualitative study of manufacturers' perspectives.
PURPOSE
The fragmented nature of the medical device market limits our understanding of how particular sub-markets navigate the device development process. Despite the widespread use of transcutaneous neuromuscular electrical stimulation (NMES), its use for acquired dysarthria treatment has not been sufficiently explored. This study aims to provide a preliminary understanding of the stages involved in the development of NMES devices designed for neurorehabilitation. It also aims to investigate manufacturers' perceptions concerning factors that facilitate or impede its development and determine its applicability for acquired dysarthria.
MATERIALS AND METHODS
In-depth semi-structured online interviews were conducted with eight NMES device manufacturers located across Europe, North America and Oceania. The interviews were video-recorded, automatically transcribed, manually reviewed, and analysed using a qualitative content analysis.
RESULTS
NMES device development for neurorehabilitation involves six complex phases with sequential and overlapping activities. Some emerging concepts were comparable to established medical device models, while others were specific to NMES. Its adaptability to different neurological disorders, the positive academia-industry collaborations, the industry's growth prospects and the promising global efforts for standardised regulations are all key facilitators for its development. However, financial, political, regulatory, and natural constraints emerged as barriers. Indications and challenges for the applicability of NMES for acquired dysarthria treatment were also discussed.
CONCLUSION
The findings provide a foundation for further investigations on the NMES market sub-sector, particularly in the context of neurorehabilitation. The study also provides insights into the potential adoption of NMES for acquired dysarthria, which can serve as a reference for future research.
PubMed: 37855610
DOI: 10.1080/17483107.2023.2269976