Residual Neural Network precisely quantifies dysarthria severity-level based on short-duration speech segments

Gupta, Siddhant; Patil, Ankur T.; Purohit, Mirali; Parmar, Mihir; Patel, Maitreya; Patil, Hemant A.; Guido, Rodrigo Capobianco

doi:10.1016/j.neunet.2021.02.008

Cited by 49 publications

(22 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As such, we conducted two comparative experiments based on both three-class and four-class tasks. We obtained 97.83% accuracy for the three-class and 97.19% for the four-class task compared to the maximum 98.90% accuracy reported in [19].…”

Section: Comparison With the State Of The Artmentioning

confidence: 59%

“…Nevertheless, because of the held-out strategy we adopted, a direct comparison with those studies that did not consider unseen speakers is not informative. To verify how our identified optimal setup compares with those reported in the literature, we have conducted a final set of experiments adopting a similar evaluation strategy considered in [19]. This would provide more confidence that the presence of unseen speakers is responsible for the variations in performance, not the optimal setup.…”

Section: Comparison With the State Of The Artmentioning

confidence: 96%

“…The framework obtained the highest recorded accuracy of over 99% on UA-Speech. Another example is [19], where short speech segments (less than 1 s) were fed to a standard CNN and a deeper CNN with residual connections. With the maximum of 1-s-long speech segments, the study reported that the residual CNN achieved 86.63% classification accuracy compared to 64.35% accuracy obtained from the standard CNN.…”

Section: Reference-free Approachesmentioning

confidence: 99%

“…In [19], 90% of the utterances from four male speakers (M01, M05, M07, M09) and four female speakers (F02, F03, F04, F05) were used for training, and the remaining 10% of the same participants' utterances for testing. The data contained all 455 distinct words, including both common and uncommon words.…”

Section: Comparison With the State Of The Artmentioning

confidence: 99%

See 3 more Smart Citations

An Investigation to Identify Optimal Setup for Automated Assessment of Dysarthric Intelligibility using Deep Learning Technologies

2022

View full text Add to dashboard Cite

Recent advances in deep learning have provided an opportunity to improve and automate dysarthria intelligibility assessment, offering a cost-effective, accessible, and less subjective way to assess dysarthric speakers. However, reviewing previous literature in the area determines that the generalization of results on new dysarthric patients was not measured properly or incomplete among the previous studies that yielded very high accuracies due to the gaps in the adopted evaluation methodologies. This is of particular importance as any practical and clinical application of intelligibility assessment approaches must reliably generalize on new patients; otherwise, the clinicians cannot accept the assessment results provided by the system deploying the approach. In this paper, after these gaps are explained, we report on our extensive investigation to propose a deep learning–based dysarthric intelligibility assessment optimal setup. Then, we explain different evaluation strategies that were applied to thoroughly verify how the optimal setup performs with new speakers and across different classes of speech intelligibility. Finally, a comparative study was conducted, benchmarking the performance of our proposed optimal setup against the state of the art by adopting similar strategies previous studies employed. Results indicate an average of 78.2% classification accuracy for unforeseen low intelligibility speakers, 40.6% for moderate intelligibility speakers, and 40.4% for high intelligibility speakers. Furthermore, we noticed a high variance of classification accuracies among individual speakers. Finally, our proposed optimal setup delivered an average of 97.19% classification accuracy when adopting a similar evaluation strategy used by the previous studies.

show abstract

Section: Comparison With the State Of The Artmentioning

confidence: 59%

Section: Comparison With the State Of The Artmentioning

confidence: 96%

Section: Reference-free Approachesmentioning

confidence: 99%

Section: Comparison With the State Of The Artmentioning

confidence: 99%

See 2 more Smart Citations

An Investigation to Identify Optimal Setup for Automated Assessment of Dysarthric Intelligibility using Deep Learning Technologies

2022

View full text Add to dashboard Cite

show abstract

“…Subsequently, several automated systems that use machine or deep learning have been developed with the aim of developing efficient tools to detect dysarthria. This approach includes automated measurement of acoustic analysis values in specific dysarthria [ 12 ], detection of disease using voice recordings [ 13 ], and assessment of severity level [ 14 ]. These methods depended on the extraction of acoustic features from speech utterances such as pitch and harmonics, shimmer, and jitter, followed by their classification using traditional machine learning methods such as Gaussian mixture model (GMM), hidden Markov model (HMM), and support vector machine (SVM).…”

Section: Introductionmentioning

confidence: 99%

Detection and differentiation of ataxic and hypokinetic dysarthria in cerebellar ataxia and parkinsonian disorders via wave splitting and integrating neural networks

et al. 2022

View full text Add to dashboard Cite

Dysarthria may present during the natural course of many degenerative neurological conditions. Hypokinetic and ataxic dysarthria are common in movement disorders and represent the underlying neuropathology. We developed an artificial intelligence (AI) model to distinguish ataxic dysarthria and hypokinetic dysarthria from normal speech and differentiate ataxic and hypokinetic speech in parkinsonian diseases and cerebellar ataxia. We screened 804 perceptual speech analyses performed in the Samsung Medical Center Neurology Department between January 2017 and December 2020. The data of patients diagnosed with parkinsonian disorders or cerebellar ataxia were included. Two speech tasks (numbering from 1 to 50 and reading nine sentences) were analyzed. We adopted convolutional neural networks and developed a patch-wise wave splitting and integrating AI system for audio classification (PWSI-AI-AC) to differentiate between ataxic and hypokinetic speech. Of the 395 speech recordings for the reading task, 76, 112, and 207 were from normal, ataxic dysarthria, and hypokinetic dysarthria subjects, respectively. Of the 409 recordings of the numbering task, 82, 111, and 216 were from normal, ataxic dysarthria, and hypokinetic dysarthria subjects, respectively. The reading and numbering task recordings were classified with 5-fold cross-validation using PWSI-AI-AC as follows: hypokinetic dysarthria vs. others (area under the curve: 0.92 ± 0.01 and 0.92 ± 0.02), ataxia vs. others (0.93 ± 0.04 and 0.89 ± 0.02), hypokinetic dysarthria vs. ataxia (0.96 ± 0.02 and 0.95 ± 0.01), hypokinetic dysarthria vs. none (0.86 ± 0.03 and 0.87 ± 0.05), and ataxia vs. none (0.87 ± 0.07 and 0.87 ± 0.09), respectively. PWSI-AI-AC showed reliable performance in differentiating ataxic and hypokinetic dysarthria and effectively augmented data to classify the types even with limited training samples. The proposed fully automatic AI system outperforms neurology residents. Our model can provide effective guidelines for screening related diseases and differential diagnosis of neurodegenerative diseases.

show abstract

Analysis and Classification Dysarthric Speech

Gupta

Patil²

2022

EAI/Springer Innovations in Communication and Computing

View full text Add to dashboard Cite

Residual Neural Network precisely quantifies dysarthria severity-level based on short-duration speech segments

Cited by 49 publications

References 61 publications

An Investigation to Identify Optimal Setup for Automated Assessment of Dysarthric Intelligibility using Deep Learning Technologies

An Investigation to Identify Optimal Setup for Automated Assessment of Dysarthric Intelligibility using Deep Learning Technologies

Detection and differentiation of ataxic and hypokinetic dysarthria in cerebellar ataxia and parkinsonian disorders via wave splitting and integrating neural networks

Analysis and Classification Dysarthric Speech

Contact Info

Product

Resources

About