Speech Recordings Research Articles

LINGUISTIC ANALYSIS OF THE NAMES OF NUTS IN THE DIALECTS OF THE MIDDLE BUG AREA

The article deals with the linguistic analysis of the names of nuts preserved in the dialects of the Middle Bug area. The object of the study is the specified layer of botanical vocabulary. The subject of the study is the phonetic, lexical-semantic and grammatical features, etymology and spatial distribution of colloquial names of nuts, their varieties (including Juglans regia L., Corylus avellana L., Arachis hypogaea L.), fruits and cultivars. The sources of the factual material are audio recordings of vernacular speech, made in 74 settlements of the Middle Bug area during the period of 2014–2016. The article uses general scientific methods of research: analysis, synthesis and observation. The expeditionary method made it possible to communicate directly with informants and record live vernacular speech using a voice recorder. Such special linguistic research methods as questionnaires and interviews contributed to the documentation of dialect speech. The descriptive method was used in the analysis of colloquial speech, while the method of linguistic geography made it possible to illustrate the areology of the recorded floranomens. We managed to record and introduce into scientific circulation 54 floranomens (taking into account descriptive constructions, phrases, diminutive forms and phonetic variants of some words), including 43 names for Juglans regia L., its fruits and cultivars, 5 names for Corylus avellana L. and 3 names for Arachis hypogaea L. Floranomens for hazel and peanut were documented on occasion. At the same time, we carried out a multilevel linguistic analysis of the corresponding floranomens, taking into account their phonetic, accentual, lexical-semantic, and partially syntactic features; clarified the motivation and etymology of the names, documented their spatial distribution in the Middle Bug area. We have provided samples of colloquial speech that complement and specify the information on nut cultivation in the surveyed area and are also valuable in terms of dialectology, phonetics, lexicology, grammar, ethnography, horticulture, etc. We drew parallels between colloquial vocabulary and the vocabulary represented in the Ukrainian literary language. The prospect of further research lays in the continuation of the description of the names of fruit trees in the dialects of the specified area.

Influence of Sensory Monitoring on Speech Breathing Planning Processes: An Exploratory Study in Aging Speakers Reporting Dyspnea.

Previous studies have suggested that inspirations during speech pauses are influenced by the length of adjacent utterances, owing to respiratory motor planning and physiological recovery processes. The goal of this study was to examine how attention to respiratory sensations may influence these processes in aging speakers with dyspnea, by measuring the effect of sensory monitoring on the relationship between utterance length and the occurrence of inspirations, as well as on functional voice and respiratory measures. Seventeen adults aged 50 years and older with complaints of voicing-related dyspnea completed a repeated-measures protocol consisting of a 2-week baseline phase and a 4-week sensory monitoring phase. Audiovisual recordings of semistructured speech and self-report questionnaires were collected at study onset, after the baseline phase, and after the sensory monitoring phase. Repeated-measures logistic regressions were conducted to examine changes in the relationship between utterance length and the occurrence of inspirations in adjacent pauses, and repeated-measures analyses of variance were used to investigate any changes in functional voice and respiratory measures. Planning and recovery processes appeared to remain constant across the baseline phase. From postbaseline to postsensory monitoring timepoints, a strengthening of the relationship between the presence of an inspiration during a speech pause and the length of the subsequent-but not preceding-utterance was noted. Significant improvements were noted in voice-related handicap from study onset to postsensory monitoring, but no changes were reported in respiratory comfort during speech. Results suggest that respiratory planning processes, that is, the ability to plan breath intakes based on the length of upcoming utterances, may be modifiable behaviorally through targeted sensory monitoring. Further studies are warranted to validate the proposed role of respiratory sensation awareness in achieving skilled temporal coordination between voicing and breathing.

A voice and speech corpus of patients who underwent upper airway surgery in pre- and post-operative states

Many research articles have explored the impact of surgical interventions on voice and speech evaluations, but advances are limited by the lack of publicly accessible datasets. To address this, a comprehensive corpus of 107 Spanish Castilian speakers was recorded, including control speakers and patients who underwent upper airway surgeries such as Tonsillectomy, Functional Endoscopic Sinus Surgery, and Septoplasty. The dataset contains 3,800 audio files, averaging 35.51 ± 5.91 recordings per patient. This resource enables systematic investigation of the effects of upper respiratory tract surgery on voice and speech. Previous studies using this corpus have shown no relevant changes in key acoustic parameters for sustained vowel phonation, consistent with initial hypotheses. However, the analysis of speech recordings, particularly nasalised segments, remains open for further research. Additionally, this dataset facilitates the study of the impact of upper airway surgery on speaker recognition and identification methods, and testing of anti-spoofing methodologies for improved robustness.

Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge

Supervised models for speech enhancement are trained using artificially generated mixtures of clean speech and noise signals. However, the synthetic training conditions may not accurately reflect real-world conditions encountered during testing. This discrepancy can result in poor performance when the test domain significantly differs from the synthetic training domain. To tackle this issue, the UDASE task of the 7th CHiME challenge aimed to leverage real-world noisy speech recordings from the test domain for unsupervised domain adaptation of speech enhancement models. Specifically, this test domain corresponds to the CHiME-5 dataset, characterized by real multi-speaker and conversational speech recordings made in noisy and reverberant domestic environments, for which ground-truth clean speech signals are not available. In this paper, we present the objective and subjective evaluations of the systems that were submitted to the CHiME-7 UDASE task, and we provide an analysis of the results. This analysis reveals a limited correlation between subjective ratings and several supervised nonintrusive performance metrics recently proposed for speech enhancement. Conversely, the results suggest that more traditional intrusive objective metrics can be used for in-domain performance evaluation using the reverberant LibriCHiME-5 dataset developed for the challenge. The subjective evaluation indicates that all systems successfully reduced the background noise, but always at the expense of increased distortion. Out of the four speech enhancement methods evaluated subjectively, only one demonstrated an improvement in overall quality compared to the unprocessed noisy speech, highlighting the difficulty of the task. The tools and audio material created for the CHiME-7 UDASE task are shared with the community.

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.

Development of a method for recognizing emotions from a speech signal

The purpose of research is automatic recognition of the speaker's emotions, based on the processing of sound recordings intended for use in alarm systems when working with operators of locomotive crews and dispatch services.Methods. Human emotion recognition has been a rapidly developing area of research in recent years. Features of the vocal tract, such as sound power, formant frequencies, are used to detect certain emotions with good accuracy. A method was used to determine the signal energy by highlighting the dominant frequency. The work has developed a program code, on the basis of which an analysis of four emotions is given - anger, joy, fear and calm. The most important and difficult step is to determine the features most suitable for distinguishing emotions and the availability of databases. Collecting databases is a complex task requiring the manifestation of sincerity of emotions. Often, the collection of a database takes place in an artificial environment and the speech may sound staged; to eliminate such problems, it is necessary to use call center recordings.Results. Recordings of basic emotional states, such as anger, joy, sadness, fear and surprise, which are the most common case of the study, were obtained and processed. The developed software code allows us to get closer to automatically determining emotions from a speech signal. To analyze speech recordings in samples, indicators of signal energy and identification of the dominant frequency were used.Conclusion. The implemented method of monitoring the emotional state of a human operator using a speech signal is widely used in the prevention and improvement of indicators of the psychophysiological professional suitability of locomotive crew workers and the preservation of their professional health. Distinct differences are observed in the characteristics of all types of emotions.

Assessment of Pepper Robot's Speech Recognition System through the Lens of Machine Learning.

Speech comprehension can be challenging due to multiple factors, causing inconvenience for both the speaker and the listener. In such situations, using a humanoid robot, Pepper, can be beneficial as it can display the corresponding text on its screen. However, prior to that, it is essential to carefully assess the accuracy of the audio recordings captured by Pepper. Therefore, in this study, an experiment is conducted with eight participants with the primary objective of examining Pepper's speech recognition system with the help of audio features such as Mel-Frequency Cepstral Coefficients, spectral centroid, spectral flatness, the Zero-Crossing Rate, pitch, and energy. Furthermore, the K-means algorithm was employed to create clusters based on these features with the aim of selecting the most suitable cluster with the help of the speech-to-text conversion tool Whisper. The selection of the best cluster is accomplished by finding the maximum accuracy data points lying in a cluster. A criterion of discarding data points with values of WER above 0.3 is imposed to achieve this. The findings of this study suggest that a distance of up to one meter from the humanoid robot Pepper is suitable for capturing the best speech recordings. In contrast, age and gender do not influence the accuracy of recorded speech. The proposed system will provide a significant strength in settings where subtitles are required to improve the comprehension of spoken statements.

A large-scale and PCR-referenced vocal audio dataset for COVID-19

The UK COVID-19 Vocal Audio Dataset is designed for the training and evaluation of machine learning models that classify SARS-CoV-2 infection status or associated respiratory symptoms using vocal audio. The UK Health Security Agency recruited voluntary participants through the national Test and Trace programme and the REACT-1 survey in England from March 2021 to March 2022, during dominant transmission of the Alpha and Delta SARS-CoV-2 variants and some Omicron variant sublineages. Audio recordings of volitional coughs, exhalations, and speech were collected in the ‘Speak up and help beat coronavirus’ digital survey alongside demographic, symptom and self-reported respiratory condition data. Digital survey submissions were linked to SARS-CoV-2 test results. The UK COVID-19 Vocal Audio Dataset represents the largest collection of SARS-CoV-2 PCR-referenced audio recordings to date. PCR results were linked to 70,565 of 72,999 participants and 24,105 of 25,706 positive cases. Respiratory symptoms were reported by 45.6% of participants. This dataset has additional potential uses for bioacoustics research, with 11.3% participants self-reporting asthma, and 27.2% with linked influenza PCR test results.

A computer-assisted tool for automatically measuring non-native Japanese oral proficiency

This study presents the development of an automated tool for assessing the speech of non-native Japanese speakers. The tool integrated an accent-trained automatic speech recording system based on deep neural networks, audio-text transcription, and natural language processing technologies to perform annotation, analysis, calculation, and scoring. A dataset consisting of audio recordings from 1000 Japanese learners across 16 countries was used for machine training. Validity and reliability tests were parallelly developed to evaluate: (a) the measures’ ability to distinguish test takers with different oral proficiency levels; (b) the agreement between the annotations and scoring performed by the tool and human raters. The results, obtained through precision, recall, F-Score, quadratically-weighted kappa, proportional reduction of mean squared error, Pearson correlation, and multi-faceted Rasch measurement, demonstrated a relatively high reliability of the automated tool. The tool provides users with both a holistic score and individual scores for each criterion, allowing them to gain insights into their overall performance as well as detailed evaluations for each aspect of their proficiency. Consequently, it can be utilized for employment, education, and self-learning purposes.

The Functioning of the English Language in the Educational, Political and Cultural Spheres of Belgium

Introduction. The English language continues to spread around the world, exhibiting a globalist function. The relevance of the presented research lies in the interest that follows from this fact in the positions of this language in countries where it is not a native or a state one. Belgium, as one of the important European centers from a socio-political point of view, is also a unique case due to the linguistic situation present in the country related to the Dutch and French languages. The purpose of this work is to analyze the position of the English language in Belgium in various areas and try to determine the trends in its development in the European state.Methodology and sources. The research materials include statistical data obtained as part of a study of the level of English language proficiency, recordings of speeches of the Prime Minister of Belgium at the UN, as well as information from the website of the Cannes Film Festival. Additionaly, results of the researchers Janssens and Hertogen concerning the language situation in Belgium are addressed. This work uses methods of synthesis and analysis, observational and descriptive methods, as well as a comparative method.Results and discussion. Belgium is one of the most advanced countries in terms of English language proficiency. Despite the existing ambiguous linguistic situation between the official languages of Belgium, English is not only able to make its way into this environment, but also has a fairly high influence. This is noticeable in the field of higher education, where, albeit with varying percentages by region, each of Belgium's most prestigious higher education institutions has programs in English. We can talk about a similar influence in the political sphere, since some major political figures in Belgium predominantly prefer English, even on those platforms where French is one of the languages of these platforms. However, the example of cinema shows that English is still poorly spread in the cultural sphere of life in Belgium.Conclusion. Younger generations of Belgium are accelerating their learning and mastery of English, playing a role in establishing very high levels of English proficiency. The contradictions that are reflected in the sphere of culture, partly in the sphere of higher education, as well as in the falling rates of language proficiency among older generations, ultimately do not alter those factors that allow us to say about the widespread and possible increase in the role of this language in the social language environment of Belgium.

PHRASE PROSODY OF A MIDDLE-RUSSIAN DIALECT: TVER

t: This paper deals with the phrase prosody of Middle-Russian dialect with оkan’je spoken in Kal’azin district of Tver region. The study, based on the material of dialectal speech recordings made in the 2019 (eight speakers born in 1933–1955, total duration — 10 hours), reveals that the intonational system of Tver idiom is quite similar to the Standard one in regard to its prosodic constituents as well as to their association to basic communicative categories — yes-no and whquestions, statements, imperatives and vocatives. We posit in it three pitch accents — one rising L+H* and two falling H*(+L) and H+L* as well as two final boundary tones (L% and H%). There is no phonological contrast between the initial boundary tones in Kal’azin dialect, this differentiates the idiom in question from more southern Russian dialects. The most specific point in the phonetic realization of the melodic contours of the narrow focus statements and the yes-no questions in Tver idiom as compared to other Middle-Russian dialects and Standard Russian is the significant variability in timing of the rising and falling pitch accents — from the very early to the very late. Based on the data studied we claim thus that the Tver dialect demonstrates the transition from the characteristic dialectal prosodic system based on level pitch accents to the standard one with contour tunes being significantly ahead of the neighbouring Pskov and Seliger-Torzhok dialects on this way to Modern Standard Russian.

A unified approach for Parkinson's disease recognition: imbalance mitigation and grid search optimized boosting with LightGBM.

The work elucidates the importance of accurate Parkinson's disease classification within medical diagnostics and introduces a novel framework for achieving this goal. Specifically, the study focuses on enhancing disease identification accuracy utilizing boosting methods. A standout contribution of this work lies in the utilization of a light gradient boosting machine (LGBM) coupled with hyperparameter tuning through grid search optimization (GSO) on the Parkinson's disease dataset derived from speech recording signals. In addition, the Synthetic Minority Over-sampling Technique (SMOTE) has also been employed as a pre-processing technique to balance the dataset, enhancing the robustness and reliability of the analysis. This approach is a novel addition to the study and underscores its potential to enhance disease identification accuracy. The datasets employed in this work include both gender-specific and combined cases, utilizing several distinctive feature subsets including baseline, Mel-frequency cepstral coefficients (MFCC), time-frequency, wavelet transform (WT), vocal fold, and tunable-Q-factor wavelet transform (TQWT). Comparative analyses against state-of-the-art boosting methods, such as AdaBoost and XG-Boost, reveal the superior performance of our proposed approach across diverse datasets and metrics. Notably, on the male cohort dataset, our method achieves exceptional results, demonstrating an accuracy of 0.98, precision of 1.00, sensitivity of 0.97, F1-Score of 0.98, and specificity of 1.00 when utilizing all features with GSO-LGBM. In comparison to AdaBoost and XGBoost, the proposed framework utilizing LGBM demonstrates superior accuracy, achieving an average improvement of 5% in classification accuracy across all feature subsets and datasets. These findings underscore the potential of the proposed methodology to enhance disease identification accuracy and provide valuable insights for further advancements in medical diagnostics.

The effect of detoxification on acoustic features of Mandarin speech in male heroin users.

This study aims to investigate the effect of detoxification on acoustic features of Mandarin speech. Speech recordings were collected from 66 male abstinent heroin users with different durations of drug detoxification, specifically early abstinent users with a detoxification duration of less than 2 years, sustained abstinent users with 2 years of detoxification, and long-term abstinent users with a detoxification duration of more than 2 years. The results of the acoustic analyses showed that early abstinent users exhibited lower loudness, relative energies of F1, F2, and F3, higher H1-A3, and fewer loudness peaks per second, as well as a longer average duration of unvoiced segments, compared to the sustained and long-term abstinent users. The findings suggest that detoxification may lead to a rehabilitation process in the speech production of abstinent heroin users (e.g., less vocal hoarseness). This study not only provides valuable insights into the effect of detoxification on speech production but also provides a theoretical basis for the speech rehabilitation and detoxification treatment of heroin users.

Listener effort quantifies clinically meaningful progression of dysarthria in people living with amyotrophic lateral sclerosis.

Amyotrophic lateral sclerosis (ALS) is a neurodegenerative motor neuron disease that causes progressive muscle weakness. Progressive bulbar dysfunction causes dysarthria and thus social isolation, reducing quality of life. The Everything ALS Speech Study obtained longitudinal clinical information and speech recordings from 292 participants. In a subset of 120 participants, we measured speaking rate (SR) and listener effort (LE), a measure of dysarthria severity rated by speech pathologists from recordings. LE intra- and inter-rater reliability was very high (ICC 0.88 to 0.92). LE correlated with other measures of dysarthria at baseline. LE changed over time in participants with ALS (slope 0.77 pts/month; p<0.001) but not controls (slope 0.005 pts/month; p=0.807). The slope of LE progression was similar in all participants with ALS who had bulbar dysfunction at baseline, regardless of ALS site of onset. LE could be a remotely collected clinically meaningful clinical outcome assessment for ALS clinical trials.

EmoBone: A Multinational Audio Dataset of Emotional Bone Conducted Speech

AbstractThis paper introduces EmoBone, a comprehensive audio‐only emotional bone‐conducted speech dataset featuring speakers from various countries. The dataset comprises speeches from 28 individuals representing 10 different nations, with each participant delivering 10 sentences designed to evoke distinct emotions. In addition to an air‐conducted microphone, the recordings utilized bone conduction technology, transmitting sound directly to the speakers' inner ears, ensuring high‐quality emotional speech recordings. To assess the validity of the dataset, 80 university students from Bangladesh listened to the recordings and successfully identified the expressed emotions with an accuracy exceeding 76%. Statistical methods were also employed to evaluate the reliability of the dataset, revealing a high level of agreement among raters. EmoBone, with a cumulative duration surpassing 19 h and 15 680 unique utterances, stands as the most extensive emotional speech dataset available. This makes it a valuable tool for studying how emotional speech varies across cultures. Furthermore, due to its utilization of bone conduction technology, EmoBone facilitates the study of acoustic features in emotional speech from diverse dimensions. The data that supports the findings of this study is available upon reasonable request. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

An exploratory characterization of speech- and fine-motor coordination in verbal children with Autism spectrum disorder

Autism spectrum disorder (ASD) is a neurodevelopmental disorder often associated with difficulties in speech production and fine-motor tasks. Thus, there is a need to develop objective measures to assess and understand speech production and other fine-motor challenges in individuals with ASD. In addition, recent research suggests that difficulties with speech production and fine-motor tasks may contribute to language difficulties in ASD. In this paper, we explore the utility of an off-body recording platform, from which we administer a speech- and fine-motor protocol to verbal children with ASD and neurotypical controls. We utilize a correlation-based analysis technique to develop proxy measures of motor coordination from signals derived from recordings of speech- and fine-motor behaviors. Eigenvalues of the resulting correlation matrix are inputs to Gaussian Mixture Models to discriminate between highly-verbal children with ASD and neurotypical controls. These eigenvalues also characterize the complexity (underlying dimensionality) of representative signals of speech- and fine-motor movement dynamics, and form the feature basis to estimate scores on an expressive vocabulary measure. Based on a pilot dataset (15 ASD and 15 controls), features derived from an oral story reading task are used in discriminating between the two groups with AUCs > 0.80, and highlight lower complexity of coordination in children with ASD. Features derived from handwriting and maze tracing tasks led to AUCs of 0.86 and 0.91, however features derived from ocular tasks did not aid in discrimination between the ASD and neurotypical groups. In addition, features derived from free speech and sustained vowel tasks are strongly correlated with expressive vocabulary scores. These results indicate the promise of a correlation-based analysis in elucidating motor differences between individuals with ASD and neurotypical controls.

Globally, songs and instrumental melodies are slower and higher and use more stable pitches than speech: A Registered Report.

Both music and language are found in all known human societies, yet no studies have compared similarities and differences between song, speech, and instrumental music on a global scale. In this Registered Report, we analyzed two global datasets: (i) 300 annotated audio recordings representing matched sets of traditional songs, recited lyrics, conversational speech, and instrumental melodies from our 75 coauthors speaking 55 languages; and (ii) 418 previously published adult-directed song and speech recordings from 209 individuals speaking 16 languages. Of our six preregistered predictions, five were strongly supported: Relative to speech, songs use (i) higher pitch, (ii) slower temporal rate, and (iii) more stable pitches, while both songs and speech used similar (iv) pitch interval size and (v) timbral brightness. Exploratory analyses suggest that features vary along a "musi-linguistic" continuum when including instrumental melodies and recited lyrics. Our study provides strong empirical evidence of cross-cultural regularities in music and speech.

Code-Mixing and Code-Switching in Online Teaching

Problems that often occur in learning need to be clarified when communicating. This is related to the use of code-mixing and connection switching in learning. This research aims to analyze the types of code-switching and code-mixing in online teaching, how English teachers use code-switching and code-mixing, and why teachers switch and mix speech. This research was conducted using a qualitative descriptive design. The objects of this research were three English teachers. Data was collected via Zoom video recording of the teacher's speech. Data were analyzed using the Miles, Huberman, and Saldana interactive model. The research results show that the type of code-switching teachers do most often is inter-sentential code-switching. There are 51 types, with a percentage of 50.49%. The code-mixing that teachers most often do is inserting (words). The total is 71 types, with a percentage of 70.29%. Finally, the most common reason teachers change and mix codes in speech is clarification of the content of speech, and the number is 8 with a percentage of 29.62%.

Evaluation of the barriers to organizational learning in a port sector company

Competitive advantage is an essential factor for the development and longevity of businesses. It is associated with companies' ability to learn, manage their knowledge, and recognize and accurately interpret opportunities and barriers to learning processes. This work aimed to identify the barriers to organizational learning in a company in the port sector. For this, an instrument was used, such as an interview script composed of 27 questions, grouped by model learning process: Intuition, interpretation, integration and institutionalization (4I) and subgrouped by influencing factors, with semi-structured questions aimed at identifying the barriers to organizational learning present in the company. The results were analyzed based on the recordings of the interviewees' speeches. The main results showed 28 of the 80 barriers listed in the adopted model, highlighting those related to the intuition process, especially those with a personal action factor, revealing opportunities for improvement in actions and mechanisms to promote the creation of knowledge and the generation of innovative ideas.

Perceptual consequences of online group speech treatment for individuals with Parkinson's disease: A pilot study case series.

We examined perceptual changes in the domains of ease of understanding, naturalness, and speech severity, as well as changes in self-perceptions of voice disability, following an online group speech treatment program for people with Parkinson's disease (PD) conducted during the COVID-19 pandemic. Seven speakers with hypokinetic dysarthria associated with PD participated in a university and community-based online group speech program for 10 weeks. Speech recordings occurred remotely 1 week before and 1 week after the online program. Thirty naïve listeners rated ease of understanding, naturalness, and speech severity based on the speech recordings. Speakers' self-perceptions of voice disability were also obtained at both time points. Individual analysis of the speech data showed that for most speakers with dysarthria, ease of understanding and perceptions of severity were rated the same or better pre- to post-treatment. Naturalness, however, was only perceived to be the same or better post-treatment in three out of seven speakers. Over half of the speakers reported improvements in their self-perception of voice disability. This pilot study highlighted the individual variability among speakers with dysarthria and the potential of online group speech treatment to maintain and/or improve speech function in this population.