Dysarthric Speech Research Articles

Increasing Motivation Increases Intelligibility Benefits of Perceptual Training in Dysarthria.

Perceptual training offers a promising, listener-targeted option for improving intelligibility of dysarthric speech. Cognitive resources are required for learning, and theoretical models of listening effort and engagement account for a role of listener motivation in allocation of such resources. Here, we manipulate training instructions to enhance motivation to test the hypothesis that increased motivation increases the intelligibility benefits of perceptual training. Across two data collection sites, which differed with respect to many elements of study design including age of speaker with dysarthria, dysarthria type and severity, type of testing and training stimuli, and participant compensation, 84 neurotypical adults were randomly assigned to one of two training instruction conditions: enhanced instructions or standard instructions. Intelligibility, quantified as percent words correct, was measured before and after training. Listeners who received the enhanced instructions achieved greater intelligibility improvements from training relative to listeners who received the standard instructions. This result was robust across data collection sites and the many differences in methodology. This study provides evidence for the role of motivation in improved understanding of dysarthric speech-increasing motivation increases allocation of cognitive resources to the learning process, resulting in improved mapping of the degraded speech signal. This provides empirical support for theoretical models of listening effort and engagement. Clinically, the results show that a simple addition to the training instructions can elevate learning outcomes.

UTran-DSR: a novel transformer-based model using feature enhancement for dysarthric speech recognition

Over the past decade, the prevalence of neurological diseases has significantly risen due to population growth and aging. Individuals suffering from spastic paralysis, brain attack, and idiopathic Parkinson’s disease (PD), among other neurological illnesses, commonly suffer from dysarthria. Early detection and treatment of dysarthria in these patients are essential for effectively managing the progression of their disease. This paper provides UTrans-DSR, a novel encoder-decoder architecture for analyzing Mel-spectrograms (generated from audios) and classifying speech as healthy or dysarthric. Our model employs transformer encoder features based on a hybrid design, which includes the feature enhancement block (FEB) and the vision transformer (ViT) encoders. This combination effectively extracts global and local pixel information regarding localization while optimizing the mel-spectrograms feature extraction process. We keep up with the original class-token grouping sequence in the vision transformer while generating a new equivalent expanding route. More specifically, two unique growing pathways use a deep-supervision approach to increase spatial data recovery and expedite model convergence. We add consecutive residual connections to the system to reduce feature loss while increasing spatial data retrieval. Our technique is based on identifying gaps in mel-spectrograms distinguishing between normal and dysarthric speech. We conducted several experiments on UTrans-DSR using the UA speech and TORGO datasets, and it outperformed the existing top models. The model performed significantly in pixel’s localized and spatial feature extraction, effectively detecting and classifying spectral gaps. The Tran-DSR model outperforms previous research models, achieving an accuracy of 97.75%.

Community-Supported Shared Infrastructure in Support of Speech Accessibility.

The Speech Accessibility Project (SAP) intends to facilitate research and development in automatic speech recognition (ASR) and other machine learning tasks for people with speech disabilities. The purpose of this article is to introduce this project as a resource for researchers, including baseline analysis of the first released data package. The project aims to facilitate ASR research by collecting, curating, and distributing transcribed U.S. English speech from people with speech and/or language disabilities. Participants record speech from their place of residence by connecting their personal computer, cell phone, and assistive devices, if needed, to the SAP web portal. All samples are manually transcribed, and 30 per participant are annotated using differential diagnostic pattern dimensions. For purposes of ASR experiments, the participants have been randomly assigned to a training set, a development set for controlled testing of a trained ASR, and a test set to evaluate ASR error rate. The SAP 2023-10-05 Data Package contains the speech of 211 people with dysarthria as a correlate of Parkinson's disease, and the associated test set contains 42 additional speakers. A baseline ASR, with a word error rate of 3.4% for typical speakers, transcribes test speech with a word error rate of 36.3%. Fine-tuning reduces the word error rate to 23.7%. Preliminary findings suggest that a large corpus of dysarthric and dysphonic speech has the potential to significantly improve speech technology for people with disabilities. By providing these data to researchers, the SAP intends to significantly accelerate research into accessible speech technology. https://doi.org/10.23641/asha.27078079.

Speech Intelligibility Outcomes Associated With Treatment for Acquired Apraxia of Speech: Magnitude of Change and Stability of Measurement.

The purpose of this investigation was to examine single-word speech intelligibility outcomes following sound production treatment in a group of 22 speakers with chronic acquired apraxia of speech (AOS) and aphasia. Also, the stability of repeated posttreatment intelligibility measures was examined for two scoring methods. The Assessment of Intelligibility of Dysarthric Speech was administered twice to each participant at pretreatment and twice at 8 weeks posttreatment. The test-retest reliability of the pretreatment samples was evaluated in a prior study; repeated samples were found to be stable over sampling times. For the current study, the three expert listeners who had rated the pretreatment samples scored the posttreatment samples using transcription and multiple-choice scoring formats. An additional expert listener, blinded to sampling time, scored pre- and posttreatment samples. The posttreatment samples were found to be stable over sampling times for the group. Posttreatment intelligibility scores were statistically significantly higher than the pretreatment scores for both scoring methods (i.e., increases of 9%-10%). Scores derived from the two scoring methods were strongly, positively correlated, with multiple-choice scores being significantly higher than transcription. The scoring methods did not differ significantly in the amount of change found from pre- to posttreatment. There were no statistically significant correlations between AOS severity and changes in pre- to posttreatment intelligibility scores. Performance for most participants was similar to group performance. Stability of posttreatment intelligibility samples supports use of intelligibility scores as outcome measures. This group of speakers demonstrated statistically significant increases in single-word speech intelligibility following sound production treatment. https://doi.org/10.23641/asha.26972425.

Accurate synthesis of dysarthric Speech for ASR data augmentation

Dysarthria is a motor speech disorder often characterized by reduced speech intelligibility through slow, uncoordinated control of speech production muscles. Automatic Speech Recognition (ASR) systems can help dysarthric talkers communicate more effectively. However, robust dysarthria-specific ASR requires a significant amount of training speech, which is not readily available for dysarthric talkers.This paper presents a new dysarthric speech synthesis method for the purpose of ASR training data augmentation. Differences in prosodic and acoustic characteristics of dysarthric spontaneous speech at varying severity levels are important components for dysarthric speech modeling, synthesis, and augmentation. For dysarthric speech synthesis, a modified neural multi-talker TTS is implemented by adding a dysarthria severity level coefficient and a pause insertion model to synthesize dysarthric speech for varying severity levels.To evaluate the effectiveness for synthesis of training data for ASR, dysarthria-specific speech recognition was used. Results show that a DNNHMM model trained on additional synthetic dysarthric speech achieves relative Word Error Rate (WER) improvement of 12.2 % compared to the baseline, and that the addition of the severity level and pause insertion controls decrease WER by 6.5 %, showing the effectiveness of adding these parameters. Overall results on the TORGO database demonstrate that using dysarthric synthetic speech to increase the amount of dysarthric-patterned speech for training has significant impact on the dysarthric ASR systems. In addition, we have conducted a subjective evaluation to evaluate the dysarthricness and similarity of synthesized speech. Our subjective evaluation shows that the perceived dysarthricness of synthesized speech is similar to that of true dysarthric speech, especially for higher levels of dysarthria. Audio samples are available at https://mohammadelc.github.io/SpeechGroupUKY/

Exploring the Impact of Fine-Tuning the Wav2vec2 Model in Database-Independent Detection of Dysarthric Speech.

Many acoustic features and machine learning models have been studied to build automatic detection systems to distinguish dysarthric speech from healthy speech. These systems can help to improve the reliability of diagnosis. However, speech recorded for diagnosis in real-life clinical conditions can differ from the training data of the detection system in terms of, for example, recording conditions, speaker identity, and language. These mismatches may lead to a reduction in detection performance in practical applications. In this study, we investigate the use of the wav2vec2 model as a feature extractor together with a support vector machine (SVM) classifier to build automatic detection systems for dysarthric speech. The performance of the wav2vec2 features is evaluated in two cross-database scenarios, language-dependent and language-independent, to study their generalizability to unseen speakers, recording conditions, and languages before and after fine-tuning the wav2vec2 model. The results revealed that the fine-tuned wav2vec2 features showed better generalization in both scenarios and gave an absolute accuracy improvement of 1.46%-8.65% compared to the non-fine-tuned wav2vec2 features.

A splice-altering homozygous variant in COX18 causes severe sensory-motor neuropathy with oculofacial apraxia

Cytochrome-c oxidase (COX) is part of the mitochondrial complex IV (CIV). COX deficiency is usually associated with tRNA variants, and less frequently with variants in COX assembly factors. Mutations in COX subunits encoded by mitochondrial DNA and nuclear DNA are rare, likely because most of them are associated to very severe phenotypes with early lethality. COX18, an assembly factor of CIV, has long been analyzed as a potential cause of mitochondrial disease. To date, only one patient has been identified carrying a homozygous missense variant in COX18, associated with neonatal encephalo-cardiomyopathy and axonal sensory neuropathy. Here, we describe a 40-year-old patient, asymptomatic until 7 months of age, who presented with progressive muscle weakness resembling spinal muscle atrophy type-2, associated with oculofacial apraxia and dysarthric speech. Electrophysiology analysis highlighted a severe sensory-motor neuropathy. Muscle biopsy showed striking and diffuse decreases of COX staining and a substantial reduction of CIV activity. Muscle biopsy showed no ragged-red fibers, although ultrastructural mitochondrial alterations were evident. A novel homozygous variant (c.598G>A), located in the last nucleotide of exon 3, was detected in COX18 by whole-exome sequencing, which affected the splicing donor site, as demonstrated by cDNA-seq. The patient fibroblasts express a truncated form of COX18 (COX18Δ112-240) capable of assembling CIV and CIV-involving supercomplexes. However, CIV activity was decreased. COX18 full-length (COX18-fl) overexpression partially rescued CIV activity in the patient fibroblasts. The rescue of the null CIV activity in COX18-KO-HEK293 cells by overexpressing of COX18Δ112-240 was significantly lower than in cells with COX18-fl. In addition, cox-18 downregulation in C. elegans resulted in slow growth and, diminished reduced motility phenotypes and as well as severe fragmentation of the mitochondrial network. Our case expands the phenotypes associated with COX18 variants and supports the pathogenic role of COX18 as the cause of a severe encephaloneuropathy syndrome.

Modeling Source and System Features Through Multi-channel Convolutional Neural Network for Improving Intelligibility Assessment of Dysarthric Speech

Modeling Source and System Features Through Multi-channel Convolutional Neural Network for Improving Intelligibility Assessment of Dysarthric Speech

Seizure freedom without seizure medication following stereoelectroencephalography implantation: a case report of drug-resistant post-traumatic epilepsy.

Achieving seizure freedom following failure of several antiseizure medications (ASMs) is rare, with the likelihood of achieving further control decreasing with each successive ASM trial. When cases of drug-resistant epilepsy arise, a diagnostic procedure known as stereoelectroencephalography (sEEG) can be used to identify epileptogenic zones (EZ) within the brain. After localization of these zones, they can be targeted for future surgical intervention. Here, we describe a case of complete seizure freedom off medication after sEEG without resection or other therapeutic intervention. In 2017, a 36-year-old right-handed male presented with drug-resistant epilepsy stemming from prior traumatic brain injury. Due to ongoing seizures, in 2020 a robotic-assisted sEEG electrode placement procedure was employed to localize the seizure onset zone. During sEEG monitoring, a single event was captured where the patient had dysarthric speech, left arm dystonic flexion, and difficulty responding to questioning. Notably, this event had no sEEG correlate, suggesting seizure occurrence in a region not monitored by implanted electrodes, which prompted the placement of scalp electrodes following this event. However, no further clinical events consistent with seizure were provoked through the remainder of recording. Following the 13-day admission, the patient chose to self-discontinue all seizure medications and has remained seizure free as of October 2023, more than 3.5 years later. While sEEG is considered a relatively safe procedure for seizure localization in drug resistant epilepsy, the possibility of microlesions created by sEEG depth electrodes remains largely unexplored. Further evaluation should be performed into potential tissue injury produced by depth electrode insertion.

Combined convolution recurrent neural network for the classification of dysarthria speech

Dysarthria is a neuromotor articulation condition that affects a person and weakens their tongue and lip muscles, and it additionally affects their capability to talk. Diffusion of factors, such as numbness, terrible coordination, and susceptible speech-generating muscle groups, can contribute to the condition. Cerebral palsy, Parkinson’s disorder, stroke, or some other kind of traumatic brain harm might also lead to dysarthria. People with dysarthria are not able to talk on a consistent basis because their speech is unclear and their phonemes are spoken irregularly because of trouble transferring the tongue, lips, and jaw as easily as in everyday speech. Dysarthric speech is stated to be 15 times slower than an ordinary speech.

Residual Convolutional Neural Network-Based Dysarthric Speech Recognition

Residual Convolutional Neural Network-Based Dysarthric Speech Recognition

Gammatonegram representation for end-to-end dysarthric speech processing tasks: speech recognition, speaker identification, and intelligibility assessment

Gammatonegram representation for end-to-end dysarthric speech processing tasks: speech recognition, speaker identification, and intelligibility assessment

AFM signal model for dysarthric speech classification using speech biomarkers.

Neurological disorders include various conditions affecting the brain, spinal cord, and nervous system which results in reduced performance in different organs and muscles throughout the human body. Dysarthia is a neurological disorder that significantly impairs an individual's ability to effectively communicate through speech. Individuals with dysarthria are characterized by muscle weakness that results in slow, slurred, and less intelligible speech production. An efficient identification of speech disorders at the beginning stages helps doctors suggest proper medications. The classification of dysarthric speech assumes a pivotal role as a diagnostic tool, enabling accurate differentiation between healthy speech patterns and those affected by dysarthria. Achieving a clear distinction between dysarthric speech and the speech of healthy individuals is made possible through the application of advanced machine learning techniques. In this work, we conducted feature extraction by utilizing the Amplitude and frequency modulated (AFM) signal model, resulting in the generation of a comprehensive array of unique features. A method involving Fourier-Bessel series expansion is employed to separate various components within a complex speech signal into distinct elements. Subsequently, the Discrete Energy Separation Algorithm is utilized to extract essential parameters, namely the Amplitude envelope and Instantaneous frequency, from each component within the speech signal. To ensure the robustness and applicability of our findings, we harnessed data from various sources, including TORGO, UA Speech, and Parkinson datasets. Furthermore, the classifier's performance was evaluated based on multiple measures such as the area under the curve, F1-Score, sensitivity, and accuracy, encompassing KNN, SVM, LDA, NB, and Boosted Tree. Our analyses resulted in classification accuracies ranging from 85 to 97.8% and the F1-score ranging between 0.90 and 0.97.

Pre-trained models for detection and severity level classification of dysarthria from speech

Automatic detection and severity level classification of dysarthria from speech enables non-invasive and effective diagnosis that helps clinical decisions about medication and therapy of patients. In this work, three pre-trained models (wav2vec2-BASE, wav2vec2-LARGE, and HuBERT) are studied to extract features to build automatic detection and severity level classification systems for dysarthric speech. The experiments were conducted using two publicly available databases (UA-Speech and TORGO). One machine learning-based model (support vector machine, SVM) and one deep learning-based model (convolutional neural network, CNN) was used as the classifier. In order to compare the performance of the wav2vec2-BASE, wav2vec2-LARGE, and HuBERT features, three popular acoustic feature sets, namely, mel-frequency cepstral coefficients (MFCCs), openSMILE and extended Geneva minimalistic acoustic parameter set (eGeMAPS) were considered. Experimental results revealed that the features derived from the pre-trained models outperformed the three baseline features. It was also found that the HuBERT features performed better than the wav2vec2-BASE and wav2vec2-LARGE features. In particular, when compared to the best-performing baseline feature (openSMILE), the HuBERT features showed in the detection problem absolute accuracy improvements that varied between 1.33% (the SVM classifier, the TORGO database) and 2.86% (the SVM classifier, the UA-Speech database). In the severity level classification problem, the HuBERT features showed absolute accuracy improvements that varied between 6.54% (the SVM classifier, the TORGO database) and 10.46% (the SVM classifier, the UA-Speech database) compared to the best-performing baseline feature (eGeMAPS).

Anticipatory coarticulation of the Spanish alveolar fricative /s/ in adults with apraxia versus dysarthria

This acoustic study compares anticipatory coarticulation characteristics of the Spanish alveolar sibilant fricative /s/ when in utterance-initial position followed by a vowel in adults with dysarthria and apraxia of speech. Three groups of participants (28 individuals with no speech disorder, 20 with dysarthria, and 8 with apraxia of speech) produced 12 monosyllabic words that included the five vowel sounds of central-peninsular Spanish. The acoustic measurements compared within and between groups were frequency of the spectral intensity peak (FreqMid) in different zones of fricative execution, magnitude of the change in frequency of the spectral intensity peak (ΔFreq) in the end zone compared to the average of the initial and middle zones, first three spectral moments, and the difference in spectral center of gravity between the middle and end zones (DiffM-E CoG). Several of these measures were able to differentiate between dysarthric and healthy speech, especially when /s/ was followed by an unrounded vowel, and the same occurred for apraxia, but this time when the adjacent vowel was rounded. While both disorders showed similar spectral patterns, the two motor speech disorders differed in terms of the measures FreqMid and DiffM-E CoG. Possible explanations for these differences are here discussed within the framework of motor control models.

Dialect identification, intelligibility ratings, and acceptability ratings of dysarthric speech in two American English dialects

ABSTRACT The current study explored the intelligibility and acceptability ratings of dysarthric speakers with African American English (AAE) and General American English (GAE) dialects by listeners who identify as GAE or AAE speakers, as well as listener ability to identify dialect in dysarthric speech. Eighty-six listeners rated the intelligibility and acceptability of sentences extracted from a passage read by speakers with dysarthria. Samples were used from the Atlanta Motor Speech Disorders Corpus and ratings were collected via self-report. The listeners identified speaker dialect in a forced-choice format. Listeners self-reported their dialect and exposure to AAE. AAE dialect was accurately identified in 63.43% of the the opportunities; GAE dialect was accurately identified in 70.35% of the opportunities. Listeners identifying as AAE speakers rated GAE speech as more acceptable, whereas, listeners identifying as GAE speakers rated AAE speech as more acceptable. Neither group of listeners demonstrated a difference in intelligibility ratings. Exposure to AAE had no effect on intelligibility or acceptability ratings. Listeners can identify dialect (AAE and GAE) with a better than chance degree of accuracy. One’s dialect may have an effect on intelligibility and acceptability ratings. Exposure to a dialect did not affect listener ratings of intelligibility or acceptability.

Dysarthria speech recognition by phonemes using hidden Markov models

The relevance of the paper is due to the difficulties of oral interaction between people with speech disorders and normotypic interlocutors as well as the low quality of abnormal speech recognition by standard speech recognition systems and the inability to create a system capable of processing any speech disorders. In this regard, this article is aimed at developing a method for automatic recognition of dysarthric speech using a pre-trained neural network for recognizing phonemes and hidden Markov models for converting phonemes into text and subsequent correction of recognition results using a search in the space of acceptable words of the nearest Levenshtein word and a dynamic algorithm for splitting the output of the model into separate words. The main advantage of using hidden Markov models in comparison with neural networks is the small size of the training data set collected individually for each user, as well as the ease of training the model further in case of progressive speech disorders. The data set for model training is described, and recommendations for collecting and marking data for model training are given. The effectiveness of the proposed method is tested on an individual data set recorded by a person with dysarthria; the recognition quality is compared with neural network models trained on the data set used. The materials of the article are of practical value for creating an augmented communication system for people with speech disorders. Keywords: hidden Markov models, dysarthria, automatic speech recognition, phonemes recognition, phoneme correction. For citation: Bredikhin B.A., Antor M.H., Khlebnikov N.A., Melnikov A.V., Bachurin M.V. Dysarthria speech recognition by phonemes using hidden Markov models. Modeling, Optimization and Information Technology. 2024;12(1). URL: https://moitvivt.ru/ru/journal/pdf?id=1471 DOI: 10.26102/2310-6018/2024.44.1.002 Распознавание дизартричной речи по фонемам с использованием скрытых марковских моделей Б.А. Бредихин1,2*, М.Х. Антор1, Н.А. Хлебников1, А.В. Мельников1, М.В. Бачурин1 1Уральский федеральный университет, Екатеринбург, Российская Федерация 2ООО «Сайберлимфа», Сколково, Российская Федерация Резюме. Актуальность работы обусловлена сложностями устного взаимодействия людей с нарушениями речи с нормотипичными собеседниками, а также низким качеством распознавания аномальной речи стандартными системами распознавания речи и невозможностью создания системы, способной обработать любые нарушения речи. В связи с этим данная статья направлена на разработку метода автоматического распознавания дизартричной речи с применением предобученной нейронной сети для распознавания фонем и скрытых марковских моделей для преобразования фонем в текст и последующей коррекции результатов распознавания с помощью поиска в пространстве допустимых слов ближайшего по расстоянию Левенштейна слова и динамического алгоритма разбиения выхода модели на отдельные слова. Основное преимущество использования скрытых марковских моделей по сравнению с нейронными сетями заключается в малом размере обучающего набора данных, собираемого индивидуально для каждого пользователя, а также в простоте дообучения модели в случае прогрессирующих нарушений речи. Описывается набор данных для обучения модели, и даются рекомендации по сбору и разметке данных для обучения модели. Эффективность предложенного метода проверяется на индивидуальном наборе данных, записанных человеком с дизартрией; качество распознавания сравнивается с нейросетевыми моделями, обученными на используемом наборе данных. Материалы статьи представляют практическую ценность для создания средства дополненной коммуникации для людей с нарушениями речи. Актуальность работы обусловлена сложностями устного взаимодействия людей с нарушениями речи с нормотипичными собеседниками, а также низким качеством распознавания аномальной речи стандартными системами распознавания речи и невозможностью создания системы, способной обработать любые нарушения речи. В связи с этим данная статья направлена на разработку метода автоматического распознавания дизартричной речи с применением предобученной нейронной сети для распознавания фонем и скрытых марковских моделей для преобразования фонем в текст и последующей коррекции результатов распознавания с помощью поиска в пространстве допустимых слов ближайшего по расстоянию Левенштейна слова и динамического алгоритма разбиения выхода модели на отдельные слова. Основное преимущество использования скрытых марковских моделей по сравнению с нейронными сетями заключается в малом размере обучающего набора данных, собираемого индивидуально для каждого пользователя, а также в простоте дообучения модели в случае прогрессирующих нарушений речи. Описывается набор данных для обучения модели, и даются рекомендации по сбору и разметке данных для обучения модели. Эффективность предложенного метода проверяется на индивидуальном наборе данных, записанных человеком с дизартрией; качество распознавания сравнивается с нейросетевыми моделями, обученными на используемом наборе данных. Материалы статьи представляют практическую ценность для создания средства дополненной коммуникации для людей с нарушениями речи.

Improving Dysarthric Speech Segmentation With Emulated and Synthetic Augmentation.

Acoustic features extracted from speech can help with the diagnosis of neurological diseases and monitoring of symptoms over time. Temporal segmentation of audio signals into individual words is an important pre-processing step needed prior to extracting acoustic features. Machine learning techniques could be used to automate speech segmentation via automatic speech recognition (ASR) and sequence to sequence alignment. While state-of-the-art ASR models achieve good performance on healthy speech, their performance significantly drops when evaluated on dysarthric speech. Fine-tuning ASR models on impaired speech can improve performance in dysarthric individuals, but it requires representative clinical data, which is difficult to collect and may raise privacy concerns. This study explores the feasibility of using two augmentation methods to increase ASR performance on dysarthric speech: 1) healthy individuals varying their speaking rate and loudness (as is often used in assessments of pathological speech); 2) synthetic speech with variations in speaking rate and accent (to ensure more diverse vocal representations and fairness). Experimental evaluations showed that fine-tuning a pre-trained ASR model with data from these two sources outperformed a model fine-tuned only on real clinical data and matched the performance of a model fine-tuned on the combination of real clinical data and synthetic speech. When evaluated on held-out acoustic data from 24 individuals with various neurological diseases, the best performing model achieved an average word error rate of 5.7% and a mean correct count accuracy of 94.4%. In segmenting the data into individual words, a mean intersection-over-union of 89.2% was obtained against manual parsing (ground truth). It can be concluded that emulated and synthetic augmentations can significantly reduce the need for real clinical data of dysarthric speech when fine-tuning ASR models and, in turn, for speech segmentation.

КЛЮЧЕВЫЕ МОМЕНТЫ ПРИМЕНЕНИЯ ВОКАЛЬНОЙ ФОНОПЕДИИ ПРИ ДИЗАРТРИЧЕСКИХ РАССТРОЙСТВАХ

In their study, the authors consider such a relevant interdisciplinary section of medical speech therapy as voice therapy (vocal rehabilitation or phono pedagogy), namely its subsection — vocal-voice therapy (vocal rehabilitation), in the context of its effect on adults with mild dysarthric disorders, which is poorly covered in the Russian specialized speech therapy literature. The article outlines the features of violations of the components of voice and speech in dysarthria. In addition to vocal-voice therapy (vocal rehabilitation) techniques, the authors emphasize the importance of including the necessary speech therapy algorithms and multimodal intervention techniques in the work. The article outlines the general principles and some technical resources for the step-by-step vocal-voice therapy (vocal rehabilitation) of students diagnosed with a symptom of dysarthria, based both on personal successful experience of many years of work and on the experience of foreign colleagues. The stages of vocal-voice therapy (vocal rehabilitation) work described by the authors include: breathing exercises to music; special vocal and vocal-voice therapy (vocal rehabilitation) exercises using piano — SOVTe exercises; traditional vocal exercises (singing the notes of a scale with an open sound); work using vocalises; work on vocal composition with words.

Direct subthalamic nucleus stimulation influences speech and voice quality in Parkinson's disease patients

BackgroundDBS of the subthalamic nucleus (STN) considerably ameliorates cardinal motor symptoms in PD. Reported STN-DBS effects on secondary dysarthric (speech) and dysphonic symptoms (voice), as originating from vocal tract motor dysfunctions, are however inconsistent with rather deleterious outcomes based on post-surgical assessments. ObjectiveTo parametrically and intra-operatively investigate the effects of deep brain stimulation (DBS) on perceptual and acoustic speech and voice quality in Parkinson's disease (PD) patients. MethodsWe performed an assessment of instantaneous intra-operative speech and voice quality changes in PD patients (n = 38) elicited by direct STN stimulations with variations of central stimulation features (depth, laterality, and intensity), separately for each hemisphere. ResultsFirst, perceptual assessments across several raters revealed that certain speech and voice symptoms could be improved with STN-DBS, but this seems largely restricted to right STN-DBS. Second, computer-based acoustic analyses of speech and voice features revealed that both left and right STN-DBS could improve dysarthric speech symptoms, but only right STN-DBS can considerably improve dysphonic symptoms, with left STN-DBS being restricted to only affect voice intensity features. Third, several subareas according to stimulation depth and laterality could be identified in the motoric STN proper and close to the associative STN with optimal (and partly suboptimal) stimulation outcomes. Fourth, low-to-medium stimulation intensities showed the most optimal and balanced effects compared to high intensities. ConclusionsSTN-DBS can considerably improve both speech and voice quality based on a carefully arranged stimulation regimen along central stimulation features.