Speech-based Estimation of Bulbar Regression in Amyotrophic Lateral Sclerosis

Wisler, Alan; Teplansky, Kristin; Green, Jordan J.; Yunusova, Yana; Campbell, Thomas F.; Heitzman, Daragh; Wang, Jun

doi:10.18653/v1/w19-1704

Cited by 8 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In clinical practice, speaking rate (number of words produced per minute, wpm) and speech intelligibility (the percentage of words that are understood by a listener) are two standards currently used to assess overall speech performance of patients with dysarthria [11]. While these measures are essential for monitoring disability and treatment planning, symptoms of bulbar dysfunction are subtle early in disease progression and often manifest before perceptual characteristics are detectable [6, 12]. Although current measures are clinically useful, it has been suggested that instrumental or performance-based measures are necessary for detecting early changes in bulbar motor function [13].…”

Section: Introductionmentioning

confidence: 99%

Tongue and Lip Acceleration as a Measure of Speech Decline in Amyotrophic Lateral Sclerosis

Teplansky¹,

Wisler²,

Green³

et al. 2022

Folia Phoniatr Logop

View full text Add to dashboard Cite

Purpose: The goal of this study was to examine the efficacy of acceleration-based articulatory measures in characterizing the decline in speech motor control due to amyotrophic lateral sclerosis (ALS). Method: Electromagnetic articulography was used to record tongue and lip movements during the production of 20 phrases. Data were collected from 50 individuals diagnosed with ALS. Articulatory kinematic variability was measured using the spatiotemporal index of both instantaneous acceleration and speed signals. Linear regression models were used to analyze the relationship between variability measures and intelligible speaking rate (a clinical measure of disease progression). A machine learning algorithm (support vector regression, SVR) was used to assess whether acceleration or speed features (e.g., mean, median, maximum) showed better performance at predicting speech severity in patients with ALS. Results: As intelligible speaking rate declined, the variability of acceleration of tongue and lip movement patterns significantly increased (p < 0.001). The variability of speed and vertical displacement did not significantly predict speech performance measures. Additionally, based on R2 and root mean square error (RMSE) values, the SVR model was able to predict speech severity more accurately from acceleration features (R2 = 0.601, RMSE = 38.453) and displacement features (R2 = 0.218, RMSE = 52.700) than from speed features (R2 = 0.554, RMSE = 40.772). Conclusion: Results from these models highlight differences in speech motor control in participants with ALS. The variability in acceleration of tongue and lip movements increases as speech performance declines, potentially reflecting physiological deviations due to the progression of ALS. Our findings suggest that acceleration is a more sensitive indicator of speech deterioration due to ALS than displacement and speed and may contribute to improved algorithm designs for monitoring disease progression from speech signals.

show abstract

Section: Introductionmentioning

confidence: 99%

Tongue and Lip Acceleration as a Measure of Speech Decline in Amyotrophic Lateral Sclerosis

Teplansky¹,

Wisler²,

Green³

et al. 2022

Folia Phoniatr Logop

View full text Add to dashboard Cite

show abstract

“…In most of the works, they use combinations of (x, y) parameters (Wang et al , 2015) or (y, z) parameters (Wang et al , 2016a) for speech analysis and these are performed for normal speakers. In few words, the authors have used (x, y, z) parameters of tongue and lip sensors (Wang et al , 2016b; Wisler et al , 2019) to perform articulatory analyzes. In Wang et al (2016b), articulatory data obtained from (x, y, z) parameters of the tongue tip, tongue back, upper and lower lips are used along with acoustic features to improve the performance of the ASR system for amyotrophic lateral sclerosis (ALS) subjects.…”

Section: Introductionmentioning

confidence: 99%

“…In Wang et al (2016b), articulatory data obtained from (x, y, z) parameters of the tongue tip, tongue back, upper and lower lips are used along with acoustic features to improve the performance of the ASR system for amyotrophic lateral sclerosis (ALS) subjects. Wisler et al (2019) used articulatory motions of tongue and lip sensors to estimate ALS functional rating scale – revised (ALSFRS-R) bulbar subscore to monitor the progression of ALS. The inclusion of articulatory data along with the acoustic data improved the performance of the support vector regression model.…”

Section: Introductionmentioning

confidence: 99%

Significant sensors and parameters in assessment of dysarthric speech

Dhanalakshmi

Nagarajan

Vijayalakshmi³

2021

View full text Add to dashboard Cite

Purpose Dysarthria is a neuromotor speech disorder caused by neuromuscular disturbances that affect one or more articulators resulting in unintelligible speech. Though inter-phoneme articulatory variations are well captured by formant frequency-based acoustic features, these variations are expected to be much higher for dysarthric speakers than normal. These substantial variations can be well captured by placing sensors in appropriate articulatory position. This study focuses to determine a set of articulatory sensors and parameters in order to assess articulatory dysfunctions in dysarthric speech. Design/methodology/approach The current work aims to determine significant sensors and parameters associated using motion path and correlation analyzes on the TORGO database of dysarthric speech. Among eight informative sensor channels and six parameters per channel in positional data, the sensors such as tongue middle, back and tip, lower and upper lips and parameters (y, z, φ) are found to contribute significantly toward capturing the articulatory information. Acoustic and positional data analyzes are performed to validate these identified significant sensors. Furthermore, a convolutional neural network-based classifier is developed for both phone-and word-level classification of dysarthric speech using acoustic and positional data. Findings The average phone error rate is observed to be lower, up to 15.54% for positional data when compared with acoustic-only data. Further, word-level classification using a combination of both acoustic and positional information is performed to study that the positional data acquired using significant sensors will boost the performance of classification even for severe dysarthric speakers. Originality/value The proposed work shows that the significant sensors and parameters can be used to assess dysfunctions in dysarthric speech effectively. The articulatory sensor data helps in better assessment than the acoustic data even for severe dysarthric speakers.

show abstract

“…Machine learning (ML) approaches that are based on a large number of acoustic speech features might be particularly well suited to detect speech changes despite the large heterogeneity in speech symptoms across patients. The studies in [18]- [23] have demonstrated that ML can detect ALS and monitor its progression based on individual speech samples. Like [18]- [23], our approach used large-space acoustic features extracted using OpenSMILE [24].…”

Section: Introductionmentioning

confidence: 99%

“…The studies in [18]- [23] have demonstrated that ML can detect ALS and monitor its progression based on individual speech samples. Like [18]- [23], our approach used large-space acoustic features extracted using OpenSMILE [24].…”

Section: Introductionmentioning

confidence: 99%

Early Identification of Speech Changes Due to Amyotrophic Lateral Sclerosis Using Machine Classification

et al. 2019

Self Cite

View full text Add to dashboard Cite

We used a machine learning (ML) approach to detect bulbar amyotrophic lateral sclerosis (ALS) prior to the onset of overt speech symptoms. The dataset included speech samples from 123 participants who were stratified by sex and into three groups: healthy controls, ALS symptomatic, and ALS presymptomatic. We compared models trained on three group pairs (symptomatic-control, presymptomatic-control, and all ALS-control participants). Using acoustic features obtained with the OpenSMILE ComParE13 configuration, we tested several feature filtering techniques. ML classification was achieved using an SVM model and leave-one-out crossvalidation. The most successful model, which was trained on symptomatic-control data, yielded an AUC=0.99 for females and AUC=0.91 for males. Models trained on all ALS-control participants had high diagnostic accuracy for classifying symptomatic and presymptomatic ALS participants (females: AUC=0.85; males: AUC=0.91). Additionally, probabilities from these models correlated with speaking rate (females: Spearman coefficient=-0.60, p<0.001; males: Spearman coefficient=-0.43, p<0.001) and intelligible speaking rate (females: Spearman coefficient=-0.65, p<0.001; males: Spearman coefficient=-0.40, p<0.01), indicating their possible use as a severity index of bulbar motor involvement in ALS. These results highlight the importance of stratifying patients by speech severity when testing diagnostic models and demonstrate the potential of ML classification in early detection and progress monitoring of ALS.

show abstract

Speech-based Estimation of Bulbar Regression in Amyotrophic Lateral Sclerosis

Cited by 8 publications

References 27 publications

Tongue and Lip Acceleration as a Measure of Speech Decline in Amyotrophic Lateral Sclerosis

Tongue and Lip Acceleration as a Measure of Speech Decline in Amyotrophic Lateral Sclerosis

Significant sensors and parameters in assessment of dysarthric speech

Early Identification of Speech Changes Due to Amyotrophic Lateral Sclerosis Using Machine Classification

Contact Info

Product

Resources

About