Speech Impairment Research Articles

Current trends in radiological diagnostics of the temporal bone pyramid pathologies

Diseases of the middle ear and the temporal bone pyramid remain one of the most common diseases in the structure of otorhinolaryngological pathologies, which have a significant impact on the quality of life of adults and children. Exudative processes, as well as their consequences, become one of the main causes of persistent hearing loss and are characterized by an asymptomatic course with a gradual evolution to chronic forms. It should be noted that in childhood the risk of impaired speech and intellectual development increases, leading to changes in the psycho-emotional status, social maladaptation of the child, and a decrease in the quality of life. Timely and complete diagnosis and high-quality follow-up takes a leading role in preventing the development of conductive hearing loss and other complicated pathologies of the temporal bone pyramid.<br /> Purpose of the study. To study the main predisposing factors, methods of radiological diagnosis and dynamic observation of patients, as well as some modern aspects of the treatment of the most common pathologies of the temporal bone pyramid.<br /> Methodology. We conducted an analytical review of open access sources from scientific databases such as Scopus, PubMed, Google Scholar, Web of Science, DisserCat, CyberLeninka. Key words used for the search: “chronic otitis media”, “cholesteatoma”, “mastoiditis”, “complications”, “magnetic resonance imaging”, “DWI”, “computed tomography”. Publications included in the literature review were full-text articles in English and Russian and dissertations in Russian. Exclusion criteria: brief reports, newspaper articles and personal communications. The search range was 5 years (2018-2023). A total of 108 sources were analyzed, of which 50 met the research objectives and inclusion criteria.<br /> Results and conclusions. In the diagnosis of temporal bone pathologies, the gold standard for diagnosis is computed tomography, but non-ionizing research techniques are increasingly used. Indications for the use of magnetic resonance imaging of the temporal bones are constantly expanding, and techniques for merging data with computed tomography data are being increasingly introduced. As a follow-up tool, magnetic resonance therapy is increasingly becoming a priority technique to reduce patient radiation exposure in the long term. In the treatment of complicated forms of diseases, endoscopic and laser correction techniques are used in foreign practice, helping to reduce the risk of recurrence and postoperative complications.<br /> <b>Key words</b>: chronic otitis media, cholesteatoma, magnetic resonance imaging, computed tomography, treatment

The Contributions of the Cerebellar Peduncles and the Frontal Aslant Tract in Mediating Speech Fluency.

Fluent speech production is a complex task that spans multiple processes, from conceptual framing and lexical access, through phonological encoding, to articulatory control. For the most part, imaging studies portraying the neural correlates of speech fluency tend to examine clinical populations sustaining speech impairments and focus on either lexical access or articulatory control, but not both. Here, we evaluated the contribution of the cerebellar peduncles to speech fluency by measuring the different components of the process in a sample of 45 neurotypical adults. Participants underwent an unstructured interview to assess their natural speaking rate and articulation rate, and completed timed semantic and phonemic fluency tasks to assess their verbal fluency. Diffusion magnetic resonance imaging with probabilistic tractography was used to segment the bilateral cerebellar peduncles (CPs) and frontal aslant tract (FAT), previously associated with speech production in clinical populations. Our results demonstrate distinct patterns of white matter associations with different fluency components. Specifically, verbal fluency is associated with the right superior CP, whereas speaking rate is associated with the right middle CP and bilateral FAT. No association is found with articulation rate in these pathways, in contrast to previous findings in persons who stutter. Our findings support the contribution of the cerebellum to aspects of speech production that go beyond articulatory control, such as lexical access, pragmatic or syntactic generation. Further, we demonstrate that distinct cerebellar pathways dissociate different components of speech fluency in neurotypical speakers.

Caregiver and child perspectives of wellbeing in school-age children with childhood apraxia of speech

Purpose Childhood apraxia of speech (CAS) is a communication deficit that impacts a child’s overall quality of life, including their academic and social interactions, yet few studies have investigated the impact from the child’s perspective. Using The World Health Organization’s International Classification of Functioning, Disability, and Health (ICF) framework, we examined the children’s and caregivers’ perspectives on the impact of CAS on their overall wellbeing. Method Survey data were collected from 32 child-caregiver dyads for children ages 9–17 years with CAS. Items elicited responses along a 5-point scale to examine the perceived impact of children’s speech impairments using the framework, including impact on communication, interpersonal interactions/relationships, and major life events. Result Results from non-parametric statistical analyses revealed: (a) caregivers reported a significantly greater impact than children across individual ICF domains; (b) child responses were not significantly correlated with their caregiver’s responses or with the child’s age, gender, or severity indicators; and (c) both caregivers and children indicated the domain of communication was impacted more than other domains. Conclusion Results suggest a potential disconnect in the perceived impact of CAS between the caregiver and child. Recommendations include facilitating a dialogue between the child-caregiver dyad and considering treatment goals that address wellbeing.

Public awareness and knowledge about speech-language pathology and communication impairments in Aotearoa New Zealand

Purpose This survey-based study explored public awareness of the speech-language pathology profession in Aotearoa New Zealand. The study also aimed to understand participants’ knowledge and experiences of individuals with speech, language, and communication impairments. Method An online survey was designed and distributed via the Qualtrics survey platform. The survey included three sections, which focused on participant demographics, awareness about speech-language pathology, and knowledge and experiences of communication impairments. Result The responses from 800 fully completed surveys were analysed. A majority of participants indicated that they had never heard or read anything about speech-language pathology and had never met a speech-language pathologist. The participants’ responses reflected low or moderate levels of understanding about the roles of speech-language pathologists and their scope of practice. Conclusion Findings indicated low levels of awareness among the general public about speech-language pathology and individuals with communication impairments. These findings were consistent with similar international research conducted over the past 4 decades. Further research is needed to support the development of initiatives designed to increase awareness of the speech-language pathology profession and the needs of individuals with communication impairments.

Unraveling the Boundaries, Overlaps, and Connections between Schizophrenia and Obsessive-Compulsive Disorder (OCD).

Schizophrenia (SCZ) and obsessive-compulsive disorder (OCD) typically have distinct diagnostic criteria and treatment approaches. SCZ is characterized by delusions, hallucinations, disorganized speech, and cognitive impairments, while OCD involves persistent, intrusive thoughts (obsessions) and repetitive behaviors (compulsions). The co-occurrence of these disorders increases clinical complexity and poses significant challenges for diagnosis and treatment. Epidemiological studies indicate a significant overlap, with prevalence rates of comorbid OCD in SCZ patients ranging from 12% to 25%, which is higher than in the general population. Etiological hypotheses suggest shared genetic, neurobiological, and environmental factors, with genetic studies identifying common loci and pathways, such as glutamatergic and dopaminergic systems. Neuroimaging studies reveal both overlapping and distinct neural abnormalities, indicating shared and unique neurobiological substrates. Environmental factors, like early life stressors and urbanicity, also contribute to the comorbidity. The overlapping clinical features of both disorders complicate diagnosis. Treatment approaches include combining SSRIs with antipsychotics and cognitive behavioral therapy (CBT). The complexity of SCZ and OCD comorbidity underscores the need for a dimensional, spectrum-based perspective on psychiatric disorders, alongside traditional categorical approaches, to improve diagnosis and treatment outcomes.

TECHNOLOGY-BASED EVALUATION IN PARKINSONISM

Parkinson's disease is a neurodegenerative disorder characterized by motor and non-motor symptoms that worsen over time. Today, traditional clinical assessment methods are used to monitor disease progression and evaluate treatment responses. However, these methods are subjective and may fail to measure specific conditions. In recent years, thanks to advances in wearable technologies, smart sensors, and data analysis, technology-based approaches to the assessment of patients with Parkinson's disease have gained more attention. With these technologies, objective data can be obtained by monitoring patients' daily activities, motor functions, and symptoms. Motor symptoms such as tremor severity, rigidity, bradykinesia, postural instabilities, freezing phenomenon, and motor parameters of speech impairment can be objectively measured through these technologies. Furthermore, the ability to remotely transmit these data allows patients to be assessed in their own homes and provides continuous feedback to healthcare professionals. This review highlights the importance and potential of technology-based assessment methods in Parkinson's patients and aims to guide future research.

Assessment of the unwanted tooth movement associated with an extended maxillary fixed retainer (3D analysis)

BackgroundPosttreatment changes after orthodontic treatment are challenging. One of the main reasons for such a phenomenon is the lack of patient compliance with removable retainers especially in the maxillary arch, due to palatal coverage, deterioration of speech, decreased masticatory efficiency, and loss of retainers. Fixed retainers have been introduced to overcome patient compliance and provide longer stable results. However, teeth still show movements when a six-unit fixed retainer is in place. Thus, in this study, an eight-unit fixed retainer was evaluated in an attempt to eliminate unwanted movements.The aim of this researchwas to assess short-term positional changes associated with an eight-unit extended maxillary fixed retainer.Materials and methodsA single-arm clinical trial was conducted to address the aim of the study. This research was approved by the institutional review board of the Faculty of Dentistry, Alexandria University (IORG:0008839, No-0479–8/2022). The registration date of this study was 5/06/2023. Twenty-eight patients (19.8 ± 4.5 years) who had finished the active orthodontic phase and started retention had an eight-unit extended maxillary fixed retainer that was bonded to the palatal surface of the maxillary incisors, canines, and the first premolars or the second premolars. Pre-retention and one-year post-retention intra-oral scans were made to produce STL files that were superimposed to determine the amount of tooth change. Additionally, analysis of digital casts and lateral cephalometric radiographs was performed.ResultsStatistically significant changes in all planes and the rotation of teeth after one year of retention were found. The upper right lateral incisor exhibited the most evident change in the vertical plane, while the upper right central incisor exhibited the greatest change overall. Minimal changes in the cast measurements were observed. Lateral cephalometric measurements showed minimal changes after one year of retention, and these changes were not statistically significant except in the interincisal angle and the angle between the upper incisor and the line connecting the A-point to the pogonion.ConclusionIncreasing the extension of maxillary fixed retainers did not eliminate unwanted tooth movement in the first year of retention.

Objective approach in the assessment of speech quality in patients with tongue cancer after hemiglossectomy

Introduction. Surgery is the leading treatment for tongue cancer, performance which leads to impaired speech function. Because speech is one of the most important tools of social interaction, its disorder can significantly affect patients’ quality of life. To date, there is no generally accepted objective approach to assessing the quality of speech that would make it possible to analyze speech changes at different stages of therapy and help in development of treatment strategy.Aim. To compare the sound reproduction of patients with tongue cancer after hemiglossectomy with and without reconstruction using an objective assessment method, namely – a special software.Materials and methods. The study included 29 patients who received surgical treatment in the volume of hemiglossectomy with ipsilateral cervical lymphodissection. The patients were divided into 2 groups: the group 1 included 14 patients who underwent reconstruction with submental, radial and buccal flaps, the group 2 – 15 patients who did not underwent it. Sound reproduction by each patient was recorded before the operation, no earlier than 10–12 days after it (session of type 1) and after the end of specialized treatment: radiation therapy, chemoradiation therapy (session of type 2). If adjuvant therapy was not prescribed, the type 2 session was performed 3–6 months after surgery. The records made during sessions of the types 1 and 2 were compared with records of preoperative session. During each session, the pronunciation of 30 syllables containing 3 problematic sounds was recorded: [k], [s] and [t] (10 syllables with each of the sounds). The differences in the data obtained during the sessions types 1 and 2 were analyzed according both the syllable set and separately for each sound studied.Results. The reconstruction performed improves sound pronunciation [t] after hemiglossectomy both after surgery and 3–6 months after the end of specialized treatment (p <0.01). After completion of specialized treatment, the pronunciation of the sound [s] significantly improved in both groups. However, in the reconstruction group, the variations in pronunciation values of this sound before the operation and after it obtained in the groups 1 and 2 were significantly reduced. During the assessment of the pronunciation of sound [k], the similar data were obtained. When comparing the quality of speech of patients during the type 2 session, the best results were obtained in group 1: in patients of this group, there were smaller mean differences in the sounds pronunciation as compared to the initial recording (p <0.001) than in patients of group 2.Conclusion. Resection of the tongue most negatively affects pronunciation of the dental-alveolar sounds than the whistling or palatine-dental sounds. The time factor has a positive effect on the speech quality of patients, therefore, the assessment of sound reproduction in patients after hemiglossectomy should be performed no earlier than 3–6 months after the end of specialized treatment.

Association between tooth loss-related speech and psychosocial impairment with cognitive function: A pilot study in Hong Kong's older population.

Tooth loss has been associated with cognitive decline, but the underlying mechanisms involving speech and psychosocial impairment remain unclear. To investigate the impact of tooth loss-related speech and psychosocial impairment on cognitive function in Hong Kong's older population. Seventy-six Cantonese-speaking participants between the ages of 51-92 were classified into three groups: patients with complete dentures (CD), partially edentulous patients with less than 10 occluding tooth pairs (OU <10), and at least 10 occluding tooth pairs (OU ≥10). Cognitive function was assessed using the Montreal Cognitive Assessment Hong Kong Version, One-minute Verbal Fluency Task and Hayling Sentence Completion Test. Objective and subjective speech assessments were carried out using artificial intelligence speech recognition algorithm and a self-designed speech questionnaire. The impact of tooth loss on psychosocial condition was evaluated by the Reading the Mind in the Eyes Test and a self-designed questionnaire. Statistical analyses (one-way ANOVA, ANCOVA, Kruskal-Wallis test, Spearman correlation test) were performed. Tooth loss was significantly associated with lower cognitive function (p = .008), speech accuracy (p = .018) and verbal fluency (p = .001). Correlations were found between cognitive function and speech accuracy (p < .0001). No significant difference in tooth loss-related psychosocial impact was found between the three groups. While warranting larger sample sizes, this pilot study highlights the need for further research on the role of speech in the association between tooth loss and cognitive function. The potential cognitive impact of tooth retention, together with its known biological and proprioceptive benefits, supports the preservation of the natural dentition.

Verbal and Non-Verbal Communication between Coach and Trainees during Swimming Lessons

The article presents the process of communication between the coach and the trainees during swimming lessons. The focus falls on verbal communication through the use of terminology specific to the sport and non-verbal communication through the implementation of particular signs. Swimming is a sport that is a 465 Биляна Рангелова, Красимира Дешева, Петър Тодоров combination of specific physical movements of the body and a specific technique for breathing and exhaling in a non-human environment – water. Furthermore, swimming is suitable for practicing by children with special educational needs and disabilities (SEND), due to the fact that it allows the achievement of social integration, on the one hand, and the development of the physical condition of the body, on the other. Practicing the sport of swimming poses various challenges, as the person with SEND may have one or more disabilities that require an individual approach. Practicing the sport in an aquatic environment further complicates the communication between a coach and a trainee. In this respect, both verbal and non- verbal communication can be used. For instance, with visually impaired children, communication involves verbal commands and instructions that must be clear and understandable. For children with impaired hearing and/or speech, communication is carried out through gestures and facial expressions similar to sign language. The article will review the literature on the problem and will provide practical examples of the application of different types of communication during swimming lessons. The article has been written as part of the activities of the project “Innovative system of verbal and non-verbal means of communication within physical education and sports activities for children with SEND”, financed by the SUMMIT Sofia University Marking Momentum for Innovation and Technological Transfer Project.

A Novel Pattern of Dystonia in DYT-VPS16: "Speaking in Tongues".

To expand the phenotype and genotype of VPS16-related dystonia (DYT-VPS16). We report 2 patients with previously unreported VPS16 truncating variants and highlight some distinctive phenomenological characteristics of DYT-VPS16. The 2 patients, who were unrelated, presented with early-onset orofacial dystonia with prominent tongue involvement. Case 1, a 37-year-old woman, developed disabling orofacial dystonia, with tongue protrusion (lingual dystonia), orofacial gesticulations, and hyperkinetic dysarthria, responsible for an odd "foreign language" quality. Case 2, a 36-year-old woman, exhibited orofacial dystonia with prominent lingual involvement and orofacial gesticulations. In both patients, orofacial dystonia led to predominant speech impairment with no or discrete swallowing difficulties. Substantial tongue dystonia may be a distinctive feature of DYT-VPS16. Our cases widen the phenotypic spectrum of DYT-VPS16 and may provide physicians with a new clinical clue for this disease.

Nutritional status of children with cerebral palsy in Ghana.

Limited knowledge on nutritional epidemiology in Ghanaian children with Cerebral Palsy (CP) necessitates a comprehensive investigation for an improved understanding of malnutrition in this population. We aimed to describe the epidemiology of malnutrition among children with CP in Ghana. The study used data collected as part of the Ghana CP Register (GCPR). The GCPR is an institution-based surveillance of children with CP aged < 18 years in Ghana. Between October 2018 and April 2020, N = 455 children with CP were registered. Data were collected on (i) weight, length or height, mid-upper-arm-circumference of children with CP; (ii) socio-demographic characteristics; (iii) motor type and topography, gross motor function classification system level (GMFCS); (iv) associated impairments; (v) educational and rehabilitation status for each child. Descriptive and bivariate analyses were performed. Mean and standard deviation age of the registered children at assessment was 5.9 ± 4.1 years, and 42.1% were female. Two-thirds of the children had ≥ one form of undernutrition (underweight or severely underweight: 38.9%, stunted or severely stunted: 51.2%, thin or severely thin: 23.8%). In the adjusted analysis, low maternal education, GMFCS-IV, speech impairment and epilepsy significantly increased the odds of undernutrition among participating children (aOR: 2.6 [95% CI:1.3-5.4]; 2.2 [95% CI:1.0-4.8]; 2.0 [95% CI:1.1-3.6]; 2.9 [95% CI:1.1-7.5] respectively). The high malnutrition rate indicates an urgent need for nutrition interventions and translational research to improve nutritional status and prevent adverse outcomes among children with CP in Ghana. Our study contributes important data and a framework to develop guidelines and evidence-based interventions for children with CP in Ghana.

Speech-language performance and comorbid disorders in children with perisylvian syndrome induced by viral encephalitis.

Viral encephalitis is one of the main causes of the perisylvian syndrome, which can cause damage to children's language-speech, feeding, and swallowing functions. Comprehensive assessment of language-speech and swallowing function and comorbidity research on these children will help children's rehabilitation workers to better understand the disease and strengthen the systematic management of comorbid disorders. To describe speech and language pathology and the occurrence of comorbid disorders in children with perisylvian syndrome induced by viral encephalitis. Twenty-two children with acquired perisylvian syndrome were recruited in this study. Language and speech functions, including oral motor function, swallowing function, language ability, and dysarthria were assessed in these patients. Craniocerebral magnetic resonance imaging (MRI), electroencephalogram examination, and intelligence evaluation were performed to determine brain lesions and comorbid disorders. All children exhibited different degrees of oral movement, dysphagia, and speech and language disorders. There was a significant difference between expressive and receptive language ability (P<0.05). There were 10, 8, and 12 children who had an intellectual disability, limb disability, and epilepsy, respectively. In addition to the damage of the peri-tegmental cortex found in MRI, thalamus lesions occurred in 19 cases and white matter involvement in six cases. Children with acquired perisylvian syndrome caused by viral encephalitis are characterized by persistent pseudobulbar dysfunction, speech and language impairment, and orofacial diplegia. They have a high probability of secondary epilepsy and are prone to motor and cognitive impairment, which need systematic management.

Can Lesions in the Right Basal Ganglia Cause Aphasia? Crossed Aphasia in a Right-Handed Patient.

Aphasia is a common neurocognitive disorder caused by impaired speech and language, with stroke being the most frequent cause. The neuroanatomical mechanism underlying this condition is not yet fully understood. This case describes a 74-year-old Caucasian woman admitted with a clinical picture of right total anterior circulation infarct (TACI) and aphasia, scoring 17 on the National Institutes of Health Stroke Scale. Neuroimaging showed a large cortico-subcortical frontotemporoparietal and insular infarct involving the basal ganglia of the right hemisphere and bilateral focal atherosclerotic stenosis on the M1 segment of the middle cerebral artery. There was no left hemispheric lesion or abnormal electric activity on the electroencephalogram. A formal evaluation was compatible with transcortical motor aphasia. The aetiological study revealed atrial fibrillation, and the case was admitted as an ischaemic stroke of undetermined aetiology with two possible causes - intracranial atherosclerotic stenosis or atrial fibrillation. Our patient fulfilled all the formal criteria for crossed aphasia in dextral (CAD): aphasia, a lesion in the right hemisphere coupled with the structural integrity of the left hemisphere, an established preference for right-hand use without a familial history of left-handedness individuals, and an absence of brain damage in childhood. Our patient's case adds to the evidence that deep structures - alone or in combination with cortical structures - are primarily affected in CAD. The diagnostic criteria for crossed aphasia in dextral (CAD) are derived from clinical case studies and include aphasia, a lesion in the right hemisphere, a strong preference for using the right hand, the structural integrity of the left hemisphere and no history of brain damage during childhood.The right lentiform nucleus was found to be the most frequent anatomical substrate involved in CAD patients, consistent with our case description.Our patient experienced transcortical motor aphasia due to a stroke in the right hemisphere, adding to the evidence that in CAD patients, deep structures are primarily affected. In contrast, in left hemispheric lesions, cortical structures seem to be the main culprits.

Natural language processing in at-risk mental states: enhancing the assessment of thought disorders and psychotic traits with semantic dynamics and graph theory.

Verbal communication has key information for mental health evaluation. Researchers have linked psychopathology phenomena to some of their counterparts in natural-language-processing (NLP). We study the characterization of subtle impairments presented in early stages of psychosis, developing new analysis techniques and a comprehensive map associating NLP features with the full range of clinical presentation. We used NLP to assess elicited and free-speech of 60 individuals in at-risk-mental-states (ARMS) and 73 controls, screened from 4,500 quota-sampled Portuguese speaking citizens in Sao Paulo, Brazil. Psychotic symptoms were independently assessed with Structured-Interview-for-Psychosis-Risk-Syndromes (SIPS). Speech features (e.g.sentiments, semantic coherence), including novel ones, were correlated with psychotic traits (Spearman's-ρ) and ARMS status (general linear models and machine-learning ensembles). NLP features were informative inputs for classification, which presented 86% balanced accuracy. The NLP features brought forth (e.g. Semantic laminarity as 'perseveration', Semantic recurrence time as 'circumstantiality', average centrality in word repetition graphs) carried most information and also presented direct correlations with psychotic symptoms. Out of the standard measures, grammatical tagging (e.g. use of adjectives) was the most relevant. Subtle speech impairments can be grasped by sensitive methods and used for ARMS screening. We sketch a blueprint for speech-based evaluation, pairing features to standard thought disorder psychometric items.

An automatic measure for speech intelligibility in dysarthrias-validation across multiple languages and neurological disorders.

Dysarthria, a motor speech disorder caused by muscle weakness or paralysis, severely impacts speech intelligibility and quality of life. The condition is prevalent in motor speech disorders such as Parkinson's disease (PD), atypical parkinsonism such as progressive supranuclear palsy (PSP), Huntington's disease (HD), and amyotrophic lateral sclerosis (ALS). Improving intelligibility is not only an outcome that matters to patients but can also play a critical role as an endpoint in clinical research and drug development. This study validates a digital measure for speech intelligibility, the ki: SB-M intelligibility score, across various motor speech disorders and languages following the Digital Medicine Society (DiMe) V3 framework. The study used four datasets: healthy controls (HCs) and patients with PD, HD, PSP, and ALS from Czech, Colombian, and German populations. Participants' speech intelligibility was assessed using the ki: SB-M intelligibility score, which is derived from automatic speech recognition (ASR) systems. Verification with inter-ASR reliability and temporal consistency, analytical validation with correlations to gold standard clinical dysarthria scores in each disease, and clinical validation with group comparisons between HCs and patients were performed. Verification showed good to excellent inter-rater reliability between ASR systems and fair to good consistency. Analytical validation revealed significant correlations between the SB-M intelligibility score and established clinical measures for speech impairments across all patient groups and languages. Clinical validation demonstrated significant differences in intelligibility scores between pathological groups and healthy controls, indicating the measure's discriminative capability. The ki: SB-M intelligibility score is a reliable, valid, and clinically relevant tool for assessing speech intelligibility in motor speech disorders. It holds promise for improving clinical trials through automated, objective, and scalable assessments. Future studies should explore its utility in monitoring disease progression and therapeutic efficacy as well as add data from further dysarthrias to the validation.

Speech impairment students and educational technology

Speech impairment students and educational technology

Co-designing the integration of voice-based conversational AI and web augmentation to amplify web inclusivity

The Web has become an essential resource but is not yet accessible to everyone. Assistive technologies and innovative, intelligent frameworks, for example, those using conversational AI, help overcome some exclusions. However, some users still experience barriers. This paper shows how a human-centered approach can shed light on technology limitations and gaps. It reports on a three-step process (focus group, co-design, and preliminary validation) that we adopted to investigate how people with speech impairments, e.g., dysarthria, browse the Web and how barriers can be reduced. The methodology helped us identify challenges and create new solutions, i.e., patterns for Web browsing, by combining voice-based conversational AI, customized for impaired speech, with techniques for the visual augmentation of web pages. While current trends in AI research focus on more and more powerful large models, participants remarked how current conversational systems do not meet their needs, and how it is important to consider each one’s specificity for a technology to be called inclusive.

Stability of ECoG high gamma signals during speech and implications for a speech BCI system in an individual with ALS: a year-long longitudinal study

Objective. Speech brain–computer interfaces (BCIs) have the potential to augment communication in individuals with impaired speech due to muscle weakness, for example in amyotrophic lateral sclerosis (ALS) and other neurological disorders. However, to achieve long-term, reliable use of a speech BCI, it is essential for speech-related neural signal changes to be stable over long periods of time. Here we study, for the first time, the stability of speech-related electrocorticographic (ECoG) signals recorded from a chronically implanted ECoG BCI over a 12 month period. Approach. ECoG signals were recorded by an ECoG array implanted over the ventral sensorimotor cortex in a clinical trial participant with ALS. Because ECoG-based speech decoding has most often relied on broadband high gamma (HG) signal changes relative to baseline (non-speech) conditions, we studied longitudinal changes of HG band power at baseline and during speech, and we compared these with residual high frequency noise levels at baseline. Stability was further assessed by longitudinal measurements of signal-to-noise ratio, activation ratio, and peak speech-related HG response magnitude (HG response peaks). Lastly, we analyzed the stability of the event-related HG power changes (HG responses) for individual syllables at each electrode. Main Results. We found that speech-related ECoG signal responses were stable over a range of syllables activating different articulators for the first year after implantation. Significance. Together, our results indicate that ECoG can be a stable recording modality for long-term speech BCI systems for those living with severe paralysis. Clinical Trial Information. ClinicalTrials.gov, registration number NCT03567213.

Automatic Speech Recognition of Conversational Speech in Individuals With Disordered Speech.

This study examines the effectiveness of automatic speech recognition (ASR) for individuals with speech disorders, addressing the gap in performance between read and conversational ASR. We analyze the factors influencing this disparity and the effect of speech mode-specific training on ASR accuracy. Recordings of read and conversational speech from 27 individuals with various speech disorders were analyzed using both (a) one speaker-independent ASR system trained and optimized for typical speech and (b) multiple ASR models that were personalized to the speech of the participants with disordered speech. Word error rates were calculated for each speech model, read versus conversational, and subject. Linear mixed-effects models were used to assess the impact of speech mode and disorder severity on ASR accuracy. We investigated nine variables, classified as technical, linguistic, or speech impairment factors, for their potential influence on the performance gap. We found a significant performance gap between read and conversational speech in both personalized and unadapted ASR models. Speech impairment severity notably impacted recognition accuracy in unadapted models for both speech modes and in personalized models for read speech. Linguistic attributes of utterances were the most influential on accuracy, though atypical speech characteristics also played a role. Including conversational speech samples in model training notably improved recognition accuracy. We observed a significant performance gap in ASR accuracy between read and conversational speech for individuals with speech disorders. This gap was largely due to the linguistic complexity and unique characteristics of speech disorders in conversational speech. Training personalized ASR models using conversational speech significantly improved recognition accuracy, demonstrating the importance of domain-specific training and highlighting the need for further research into ASR systems capable of handling disordered conversational speech effectively.