Responsible development of clinical speech AI: Bridging the gap between clinical research and technology.

This perspective article explores the challenges and potential of using speech as a biomarker in clinical settings, particularly when constrained by the small clinical datasets typically available in such contexts. We contend that by integrating insights from speech science and clinical research, we can reduce sample complexity in clinical speech AI models with the potential to decrease timelines to translation. Most existing models are based on high-dimensional feature representations trained with limited sample sizes and often do not leverage insights from speech science and clinical research. This approach can lead to overfitting, where the models perform exceptionally well on training data but fail to generalize to new, unseen data. Additionally, without incorporating theoretical knowledge, these models may lack interpretability and robustness, making them challenging to troubleshoot or improve post-deployment. We propose a framework for organizing health conditions based on their impact on speech and promote the use of speech analytics in diverse clinical contexts beyond cross-sectional classification. For high-stakes clinical use cases, we advocate for a focus on explainable and individually-validated measures and stress the importance of rigorous validation frameworks and ethical considerations for responsible deployment. Bridging the gap between AI research and clinical speech research presents new opportunities for more efficient translation of speech-based AI tools and advancement of scientific discoveries in this interdisciplinary space, particularly if limited to small or retrospective datasets.

The impact of headache intensity on speech in participants with migraine and acute post-traumatic headache.

BACKGROUND: Slower speaking rates and higher pause rates are found in individuals with migraine or post-traumatic headache during headache compared to when headache-free. We aimed to determine whether headache intensity influences the speaking rate and pause rate of participants with migraine or acute post-traumatic headache (aPTH) following mild traumatic brain injury (mTBI). METHODS: Using a speech elicitation tool, participants with migraine, aPTH, and healthy controls (HC) submitted speech samples over a period of 3 months. Speaking and pause rates were calculated when participants were headache-free and when they had mild or moderate headache. In this observational study, speaking and pause rates in participants with migraine and aPTH were compared to HC, controlling for age, sex, and days since mTBI (participants with aPTH only). RESULTS: A total of 2902 longitudinal speech samples from 13 individuals with migraine (mean age = 33.5, SD = 6.6; 12 females/1 male), 43 individuals with aPTH (mean age = 44.4, SD = 13.5; 28 females/15 males), and 56 HC (mean age = 40.8, SD = 13.0; 36 females/20 males) were collected. There was no difference in speaking rate between HC and the combined headache cohort of participants (migraine and aPTH) when they had headache freedom or a mild headache. When participants had moderate intensity headache, their speaking rate was significantly slower compared to that of HC and compared to their speaking rate during mild headache intensity or headache freedom. For the combined headache cohort of participants, pause rates were significantly higher when they had headache freedom or had a headache of mild or moderate intensity relative to HC. Compared to participants' pause rate during headache freedom, their pause rate was significantly higher during mild and moderate headache intensity. Participants with aPTH had significantly slower speaking rates compared to participants with migraine during headache freedom, mild headache intensity, and moderate headache intensity. Participants with aPTH had significantly higher pause rates compared to participants with migraine when experiencing moderate headache intensity. DISCUSSION: For both aPTH and migraine, more severe headache pain was associated with higher pause rates and slower speaking rates, suggesting that speaking rate and pause rate could serve as objective biomarkers for headache-related pain. Slower speaking rate in participants with aPTH could reflect additional consequences of TBI-related effects on motor control and speech production.

Automated speech analytics in ALS: higher sensitivity of digital articulatory precision over the ALSFRS-R.

Objective: Although studies have shown that digital measures of speech detected ALS speech impairment and correlated with the ALSFRS-R speech item, no study has yet compared their performance in detecting speech changes. In this study, we compared the performances of the ALSFRS-R speech item and an algorithmic speech measure in detecting clinically important changes in speech. Importantly, the study was part of a FDA submission which received the breakthrough device designation for monitoring ALS; we provide this paper as a roadmap for validating other speech measures for monitoring disease progression. Methods: We obtained ALSFRS-R speech subscores and speech samples from participants with ALS. We computed the minimum detectable change (MDC) of both measures; using clinician-reported listener effort and a perceptual ratings of severity, we calculated the minimal clinically important difference (MCID) of each measure with respect to both sets of clinical ratings. Results: For articulatory precision, the MDC (.85) was lower than both MCID measures (2.74 and 2.28), and for the ALSFRS-R speech item, MDC (.86) was greater than both MCID measures (.82 and .72), indicating that while the articulatory precision measure detected minimal clinically important differences in speech, the ALSFRS-R speech item did not. Conclusion: The results demonstrate that the digital measure of articulatory precision effectively detects clinically important differences in speech ratings, outperforming the ALSFRS-R speech item. Taken together, the results herein suggest that this speech outcome is a clinically meaningful measure of speech change.

Operationalizing Clinical Speech Analytics: Moving From Features to Measures for Real-World Clinical Impact.

OBJECTIVE: This research note advocates for a methodological shift in clinical speech analytics, emphasizing the transition from high-dimensional speech feature representations to clinically validated speech measures designed to operationalize clinically relevant constructs of interest. The aim is to enhance model generalizability and clinical applicability in real-world settings. METHOD: We outline the challenges of using conventional supervised machine learning models in clinical speech analytics, particularly their limited generalizability and interpretability. We propose a new framework focusing on speech measures that are closely tied to specific speech constructs and have undergone rigorous validation. This research note discusses a case study involving the development of a measure for articulatory precision in amyotrophic lateral sclerosis (ALS), detailing the process from ideation through Food and Drug Administration (FDA) breakthrough status designation. RESULTS: The case study demonstrates how the operationalization of the articulatory precision construct into a quantifiable measure yields robust, clinically meaningful results. The measure's validation followed the V3 framework (verification, analytical validation, and clinical validation), showing high correlation with clinical status and speech intelligibility. The practical application of these measures is exemplified in a clinical trial and designation by the FDA as a breakthrough status device, underscoring their real-world impact. CONCLUSIONS: Transitioning from speech features to speech measures offers a more targeted approach for developing speech analytics tools in clinical settings. This shift ensures that models are not only technically sound but also clinically relevant and interpretable, thereby bridging the gap between laboratory research and practical health care applications. We encourage further exploration and adoption of this approach for developing interpretable speech representations tailored to specific clinical needs.

Electroencephalographic Classification Reveals Atypical Speech Motor Planning in Stuttering Adults.

PURPOSE: This study explores speech motor planning in adults who stutter (AWS) and adults who do not stutter (ANS) by applying machine learning algorithms to electroencephalographic (EEG) signals. In this study, we developed a technique to holistically examine neural activity differences in speaking and silent reading conditions across the entire cortical surface. This approach allows us to test the hypothesis that AWS will exhibit lower separability of the speech motor planning condition. METHOD: We used the silent reading condition as a control condition to isolate speech motor planning activity. We classified EEG signals from AWS and ANS individuals into speaking and silent reading categories using kernel support vector machines. We used relative complexities of the learned classifiers to compare speech motor planning discernibility for both classes. RESULTS: AWS group classifiers require a more complex decision boundary to separate speech motor planning and silent reading classes. CONCLUSIONS: These findings indicate that the EEG signals associated with speech motor planning are less discernible in AWS, which may result from altered neuronal dynamics in AWS. Our results support the hypothesis that AWS exhibit lower inherent separability of the silent reading and speech motor planning conditions. Further investigation may identify and compare the features leveraged for speech motor classification in AWS and ANS. These observations may have clinical value for developing novel speech therapies or assistive devices for AWS.

Reliability and validity of a widely-available AI tool for assessment of stress based on speech.

Cigna's online stress management toolkit includes an AI-based tool that purports to evaluate a person's psychological stress level based on analysis of their speech, the Cigna StressWaves Test (CSWT). In this study, we evaluate the claim that the CSWT is a "clinical grade" tool via an independent validation. The results suggest that the CSWT is not repeatable and has poor convergent validity; the public availability of the CSWT despite insufficient validation data highlights concerns regarding premature deployment of digital health tools for stress and anxiety management.

Robust Vocal Quality Feature Embeddings for Dysphonic Voice Detection.

Approximately 1.2% of the world's population has impaired voice production. As a result, automatic dysphonic voice detection has attracted considerable academic and clinical interest. However, existing methods for automated voice assessment often fail to generalize outside the training conditions or to other related applications. In this paper, we propose a deep learning framework for generating acoustic feature embeddings sensitive to vocal quality and robust across different corpora. A contrastive loss is combined with a classification loss to train our deep learning model jointly. Data warping methods are used on input voice samples to improve the robustness of our method. Empirical results demonstrate that our method not only achieves high in-corpus and cross-corpus classification accuracy but also generates good embeddings sensitive to voice quality and robust across different corpora. We also compare our results against three baseline methods on clean and three variations of deteriorated in-corpus and cross-corpus datasets and demonstrate that the proposed model consistently outperforms the baseline methods.

Wav2DDK: Analytical and Clinical Validation of an Automated Diadochokinetic Rate Estimation Algorithm on Remotely Collected Speech.

PURPOSE: Oral diadochokinesis is a useful task in assessment of speech motor function in the context of neurological disease. Remote collection of speech tasks provides a convenient alternative to in-clinic visits, but scoring these assessments can be a laborious process for clinicians. This work describes Wav2DDK, an automated algorithm for estimating the diadochokinetic (DDK) rate on remotely collected audio from healthy participants and participants with amyotrophic lateral sclerosis (ALS). METHOD: Wav2DDK was developed using a corpus of 970 DDK assessments from healthy and ALS speakers where ground truth DDK rates were provided manually by trained annotators. The clinical utility of the algorithm was demonstrated on a corpus of 7,919 assessments collected longitudinally from 26 healthy controls and 82 ALS speakers. Corpora were collected via the participants' own mobile device, and instructions for speech elicitation were provided via a mobile app. DDK rate was estimated by parsing the character transcript from a deep neural network transformer acoustic model trained on healthy and ALS speech. RESULTS: Algorithm estimated DDK rates are highly accurate, achieving .98 correlation with manual annotation, and an average error of only 0.071 syllables per second. The rate exactly matched ground truth for 83% of files and was within 0.5 syllables per second for 95% of files. Estimated rates achieve a high test-retest reliability (r = .95) and show good correlation with the revised ALS functional rating scale speech subscore (r = .67). CONCLUSION: We demonstrate a system for automated DDK estimation that increases efficiency of calculation beyond manual annotation. Thorough analytical and clinical validation demonstrates that the algorithm is not only highly accurate, but also provides a convenient, clinically relevant metric for tracking longitudinal decline in ALS, serving to promote participation and diversity of participants in clinical research. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.23787033.

A speech-based prognostic model for dysarthria progression in ALS.

Objective: We demonstrated that it was possible to predict ALS patients' degree of future speech impairment based on past data. We used longitudinal data from two ALS studies where participants recorded their speech on a daily or weekly basis and provided ALSFRS-R speech subscores on a weekly or quarterly basis (quarter-annually). Methods: Using their speech recordings, we measured articulatory precision (a measure of the crispness of pronunciation) using an algorithm that analyzed the acoustic signal of each phoneme in the words produced. First, we established the analytical and clinical validity of the measure of articulatory precision, showing that the measure correlated with perceptual ratings of articulatory precision (r = .9). Second, using articulatory precision from speech samples from each participant collected over a 45-90 day model calibration period, we showed it was possible to predict articulatory precision 30-90 days after the last day of the model calibration period. Finally, we showed that the predicted articulatory precision scores mapped onto ALSFRS-R speech subscores. Results: the mean absolute error was as low as 4% for articulatory precision and 14% for ALSFRS-R speech subscores relative to the total range of their respective scales. Conclusion: Our results demonstrated that a subject-specific prognostic model for speech predicts future articulatory precision and ALSFRS-R speech values accurately.

A neuropsychological approach to differentiating cannabis-induced and primary psychotic disorders.

AIM: Rates of cannabis use are elevated in early psychosis populations, rendering it difficult to determine if an episode of psychosis is related to cannabis use (e.g., cannabis-induced psychosis), or if substance use is co-occurring with a primary psychotic disorder (e.g., schizophrenia). Clinical presentations of these disorders are often indistinguishable, hindering assessment and treatment. Despite substantial research identifying cognitive deficits, eye movement abnormalities and speech impairment associated with primary psychotic disorders, these neuropsychological features have not been explored as targets for diagnostic differentiation in early psychosis. METHODS: Eighteen participants with cannabis-induced psychosis (Mage  = 21.9, SDage  = 4.25, 14 male) and 19 participants with primary psychosis (Mage  = 29.2, SDage  = 7.65, 17 male) were recruited from early intervention programs. Diagnoses were ascertained by primary treatment teams after a minimum of 6 months in the program. Participants completed tasks assessing cognitive performance, saccadic eye movements and speech. Clinical symptoms, trauma, substance use, premorbid functioning and illness insight were also assessed. RESULTS: Relative to individuals with primary psychosis, individuals with cannabis-induced psychosis demonstrated significantly better performance on the pro-saccade task, faster RT on pro- and anti-saccade tasks, better premorbid adjustment, and a higher degree of insight into their illness. There were no significant differences between groups on psychiatric symptoms, premorbid intellectual functioning, or problems related to cannabis use. CONCLUSIONS: In early stages of illness, reliance on traditional diagnostic tools or clinical interviews may be insufficient to distinguish between cannabis-induced and primary psychosis. Future research should continue to explore neuropsychological differences between these diagnoses to improve diagnostic accuracy.

Questionnaire and structural imaging data accurately predict headache improvement in patients with acute post-traumatic headache attributed to mild traumatic brain injury.

BACKGROUND: Our prior work demonstrated that questionnaires assessing psychosocial symptoms have utility for predicting improvement in patients with acute post-traumatic headache following mild traumatic brain injury. In this cohort study, we aimed to determine whether prediction accuracy can be refined by adding structural magnetic resonance imaging (MRI) brain measures to the model. METHODS: Adults with acute post-traumatic headache (enrolled 0-59 days post-mild traumatic brain injury) underwent T1-weighted brain MRI and completed three questionnaires (Sports Concussion Assessment Tool, Pain Catastrophizing Scale, and the Trait Anxiety Inventory Scale). Individuals with post-traumatic headache completed an electronic headache diary allowing for determination of headache improvement at three- and at six-month follow-up. Questionnaire and MRI measures were used to train prediction models of headache improvement and headache trajectory. RESULTS: Forty-three patients with post-traumatic headache (mean age = 43.0, SD = 12.4; 27 females/16 males) and 61 healthy controls were enrolled (mean age = 39.1, SD = 12.8; 39 females/22 males). The best model achieved cross-validation Area Under the Curve of 0.801 and 0.805 for predicting headache improvement at three and at six months. The top contributing MRI features for the prediction included curvature and thickness of superior, middle, and inferior temporal, fusiform, inferior parietal, and lateral occipital regions. Patients with post-traumatic headache who did not improve by three months had less thickness and higher curvature measures and notably greater baseline differences in brain structure vs. healthy controls (thickness: p < 0.001, curvature: p = 0.012) than those who had headache improvement. CONCLUSIONS: A model including clinical questionnaire data and measures of brain structure accurately predicted headache improvement in patients with post-traumatic headache and achieved improvement compared to a model developed using questionnaire data alone.

Speech Entrainment in Adolescent Conversations: A Developmental Perspective.

PURPOSE: Defined as the similarity of speech behaviors between interlocutors, speech entrainment plays an important role in successful adult conversations. According to theoretical models of entrainment and research on motoric, cognitive, and social developmental milestones, the ability to entrain should develop throughout adolescence. However, little is known about the specific developmental trajectory or the role of speech entrainment in conversational outcomes of this age group. The purpose of this study is to characterize speech entrainment patterns in the conversations of neurotypical early adolescents. METHOD: This study utilized a corpus of 96 task-based conversations between adolescents between the ages of 9 and 14 years and a comparison corpus of 32 task-based conversations between adults. For each conversational turn, two speech entrainment scores were calculated for 429 acoustic features across rhythmic, articulatory, and phonatory dimensions. Predictive modeling was used to evaluate the degree of entrainment and relationship between entrainment and two metrics of conversational success. RESULTS: Speech entrainment increased throughout early adolescence but did not reach the level exhibited in conversations between adults. Additionally, speech entrainment was predictive of both conversational quality and conversational efficiency. Furthermore, models that included all acoustic features and both entrainment types performed better than models that only included individual acoustic feature sets or one type of entrainment. CONCLUSIONS: Our findings show that speech entrainment skills are largely developed during early adolescence with continued development possibly occurring across later adolescence. Additionally, results highlight the role of speech entrainment in successful conversation in this population, suggesting the import of continued exploration of this phenomenon in both neurotypical and neurodivergent adolescents. We also provide evidence of the value of using holistic measures that capture the multidimensionality of speech entrainment and provide a validated methodology for investigating entrainment across multiple acoustic features and entrainment types.

Language Analytics for Assessment of Mental Health Status and Functional Competency.

BACKGROUND AND HYPOTHESIS: Automated language analysis is becoming an increasingly popular tool in clinical research involving individuals with mental health disorders. Previous work has largely focused on using high-dimensional language features to develop diagnostic and prognostic models, but less work has been done to use linguistic output to assess downstream functional outcomes, which is critically important for clinical care. In this work, we study the relationship between automated language composites and clinical variables that characterize mental health status and functional competency using predictive modeling. STUDY DESIGN: Conversational transcripts were collected from a social skills assessment of individuals with schizophrenia (n = 141), bipolar disorder (n = 140), and healthy controls (n = 22). A set of composite language features based on a theoretical framework of speech production were extracted from each transcript and predictive models were trained. The prediction targets included clinical variables for assessment of mental health status and social and functional competency. All models were validated on a held-out test sample not accessible to the model designer. STUDY RESULTS: Our models predicted the neurocognitive composite with Pearson correlation PCC = 0.674; PANSS-positive with PCC = 0.509; PANSS-negative with PCC = 0.767; social skills composite with PCC = 0.785; functional competency composite with PCC = 0.616. Language features related to volition, affect, semantic coherence, appropriateness of response, and lexical diversity were useful for prediction of clinical variables. CONCLUSIONS: Language samples provide useful information for the prediction of a variety of clinical variables that characterize mental health status and functional competency.

TorchDIVA: An extensible computational model of speech production built on an open-source machine learning library.

The DIVA model is a computational model of speech motor control that combines a simulation of the brain regions responsible for speech production with a model of the human vocal tract. The model is currently implemented in Matlab Simulink; however, this is less than ideal as most of the development in speech technology research is done in Python. This means there is a wealth of machine learning tools which are freely available in the Python ecosystem that cannot be easily integrated with DIVA. We present TorchDIVA, a full rebuild of DIVA in Python using PyTorch tensors. DIVA source code was directly translated from Matlab to Python, and built-in Simulink signal blocks were implemented from scratch. After implementation, the accuracy of each module was evaluated via systematic block-by-block validation. The TorchDIVA model is shown to produce outputs that closely match those of the original DIVA model, with a negligible difference between the two. We additionally present an example of the extensibility of TorchDIVA as a research platform. Speech quality enhancement in TorchDIVA is achieved through an integration with an existing PyTorch generative vocoder called DiffWave. A modified DiffWave mel-spectrum upsampler was trained on human speech waveforms and conditioned on the TorchDIVA speech production. The results indicate improved speech quality metrics in the DiffWave-enhanced output as compared to the baseline. This enhancement would have been difficult or impossible to accomplish in the original Matlab implementation. This proof-of-concept demonstrates the value TorchDIVA can bring to the research community. Researchers can download the new implementation at: https://github.com/skinahan/DIVA_PyTorch.

Dysarthria detection based on a deep learning model with a clinically-interpretable layer.

Studies have shown deep neural networks (DNN) as a potential tool for classifying dysarthric speakers and controls. However, representations used to train DNNs are largely not clinically interpretable, which limits clinical value. Here, a model with a bottleneck layer is trained to jointly learn a classification label and four clinically-interpretable features. Evaluation of two dysarthria subtypes shows that the proposed method can flexibly trade-off between improved classification accuracy and discovery of clinically-interpretable deficit patterns. The analysis using Shapley additive explanation shows the model learns a representation consistent with the disturbances that define the two dysarthria subtypes considered in this work.

Thalamic subfield iron accumulation after acute mild traumatic brain injury as a marker of future post-traumatic headache intensity.

OBJECTIVE: To explore alterations in thalamic subfield volume and iron accumulation in individuals with post-traumatic headache (PTH) relative to healthy controls. BACKGROUND: The thalamus plays a pivotal role in the pathomechanism of pain and headache, yet the role of the thalamus in PTH attributed to mild traumatic brain injury (mTBI) remains unclear. METHODS: A total of 107 participants underwent multimodal T1-weighted and T2* brain magnetic resonance imaging. Using a clinic-based observational study, thalamic subfield volume and thalamic iron accumulation were explored in 52 individuals with acute PTH (mean age = 41.3; standard deviation [SD] = 13.5), imaged on average 24 days post mTBI, and compared to 55 healthy controls (mean age = 38.3; SD = 11.7) without history of mTBI or migraine. Symptoms of mTBI and headache characteristics were assessed at baseline (0-59 days post mTBI) (n = 52) and 3 months later (n = 46) using the Symptom Evaluation of the Sports Concussion Assessment Tool (SCAT-5) and a detailed headache history questionnaire. RESULTS: Relative to controls, individuals with acute PTH had significantly less volume in the lateral geniculate nucleus (LGN) (mean volume: PTH = 254.1, SD = 43.4 vs. controls = 278.2, SD = 39.8; p = 0.003) as well as more iron deposition in the left LGN (PTH: T2* signal = 38.6, SD = 6.5 vs. controls: T2* signal = 45.3, SD = 2.3; p = 0.048). Correlations in individuals with PTH revealed a positive relationship between left LGN T2* iron deposition and SCAT-5 symptom severity score at baseline (r = -0.29, p = 0.019) and maximum headache intensity at the 3-month follow-up (r = -0.47, p = 0.002). CONCLUSION: Relative to healthy controls, individuals with acute PTH had less volume and higher iron deposition in the left LGN. Higher iron deposition in the left LGN might reflect mTBI severity and poor headache recovery.

Developing multivariable models for predicting headache improvement in patients with acute post-traumatic headache attributed to mild traumatic brain injury: A preliminary study.

OBJECTIVES/BACKGROUND: Post-traumatic headache (PTH) is a common symptom after mild traumatic brain injury (mTBI). Although there have been several studies that have used clinical features of PTH to attempt to predict headache recovery, currently no accurate methods exist for predicting individuals' improvement from acute PTH. This study investigated the utility of clinical questionnaires for predicting (i) headache improvement at 3 and 6 months, and (ii) headache trajectories over the first 3 months. METHODS: We conducted a clinic-based observational longitudinal study of patients with acute PTH who completed a battery of clinical questionnaires within 0-59 days post-mTBI. The battery included headache history, symptom evaluation, cognitive tests, psychological tests, and scales assessing photosensitivity, hyperacusis, insomnia, cutaneous allodynia, and substance use. Each participant completed a web-based headache diary, which was used to determine headache improvement. RESULTS: Thirty-seven participants with acute PTH (mean age = 42.7, standard deviation [SD] = 12.0; 25 females/12 males) completed questionnaires at an average of 21.7 (SD = 13.1) days post-mTBI. The classification of headache improvement or non-improvement at 3 and 6 months achieved cross-validation area under the curve (AUC) of 0.72 (95% confidence interval [CI] 0.55 to 0.89) and 0.84 (95% CI 0.66 to 1.00). Sub-models trained using only the top five features still achieved 0.72 (95% CI 0.55 to 0.90) and 0.77 (95% CI 0.52 to 1.00) AUC. The top five contributing features were from three questionnaires: Pain Catastrophizing Scale total score and helplessness sub-domain score; Sports Concussion Assessment Tool Symptom Evaluation total score and number of symptoms; and the State-Trait Anxiety Inventory score. The functional regression model achieved R = 0.64 for modeling headache trajectory over the first 3 months. CONCLUSION: Questionnaires completed following mTBI have good utility for predicting headache improvement at 3 and 6 months in the future as well as the evolving headache trajectory. Reducing the battery to only three questionnaires, which assess post-concussive symptom load and biopsychosocialecologic factors, was helpful to determine a reasonable prediction accuracy for headache improvement.

Consonant-Vowel Transition Models Based on Deep Learning for Objective Evaluation of Articulation.

Spectro-temporal dynamics of consonant-vowel (CV) transition regions are considered to provide robust cues related to articulation. In this work, we propose an objective measure of precise articulation, dubbed the objective articulation measure (OAM), by analyzing the CV transitions segmented around vowel onsets. The OAM is derived based on the posteriors of a convolutional neural network pre-trained to classify between different consonants using CV regions as input. We demonstrate that the OAM is correlated with perceptual measures in a variety of contexts including (a) adult dysarthric speech, (b) the speech of children with cleft lip/palate, and (c) a database of accented English speech from native Mandarin and Spanish speakers.

The Effects of Intensive Voice Treatment in Mandarin Speakers With Parkinson's Disease: Acoustic and Perceptual Findings.

PURPOSE: This study investigated the effects of intensive voice treatment on subjective and objective measures of speech production in Mandarin speakers with hypokinetic dysarthria. METHOD: Nine Mandarin speakers with hypokinetic dysarthria due to Parkinson's disease received 4 weeks of intensive voice treatment (4 × 60 min per week). The speakers were recorded reading a passage before treatment (PRE), immediately after treatment (POST), and at 6-month follow-up (FU). Listeners (n = 15) rated relative ease of understanding (EOU) of paired speech samples on a visual analogue scale. Acoustic analyses were performed. Changes in EOU, vocal intensity, global and local fundamental frequency (f o) variation, speech rate, and acoustic vowel space area (VSA) were examined. RESULTS: Increases were found in EOU and vocal intensity from PRE to POST and from PRE to FU, with no change found from POST to FU. Speech rate increased from PRE to POST, with limited evidence of an increase from PRE to FU and no change from POST to FU. No changes in global or local f o variation or in VSA were found. CONCLUSIONS: Intensive voice treatment shows promise for improving speech production in Mandarin speakers with hypokinetic dysarthria. Vocal intensity, speech rate, and, crucially, intelligibility, may improve for up to 6 months posttreatment. In contrast, f o variation and VSA may not increase following the treatment. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.19529017.

Automated semantic relevance as an indicator of cognitive decline: Out-of-sample validation on a large-scale longitudinal dataset.

We developed and evaluated an automatically extracted measure of cognition (semantic relevance) using automated and manual transcripts of audio recordings from healthy and cognitively impaired participants describing the Cookie Theft picture from the Boston Diagnostic Aphasia Examination. We describe the rationale and metric validation. We developed the measure on one dataset and evaluated it on a large database (>2000 samples) by comparing accuracy against a manually calculated metric and evaluating its clinical relevance. The fully automated measure was accurate (r = .84), had moderate to good reliability (intra-class correlation = .73), correlated with Mini-Mental State Examination and improved the fit in the context of other automatic language features (r = .65), and longitudinally declined with age and level of cognitive impairment. This study demonstrates the use of a rigorous analytical and clinical framework for validating automatic measures of speech, and applied it to a measure that is accurate and clinically relevant.