Automated Dysarthria Severity Classification: A Study on Acoustic Features and Deep Learning Techniques
Assessing the severity level of dysarthria can provide an insight into the patient’s improvement, assist pathologists to plan therapy, and aid automatic dysarthric speech recognition systems. In this article, we present a comparative study on the classification of dysarthria severity leve...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9762324/ |
| _version_ | 1797805260334432256 |
|---|---|
| author | Amlu Anna Joshy Rajeev Rajan |
| author_facet | Amlu Anna Joshy Rajeev Rajan |
| author_sort | Amlu Anna Joshy |
| collection | DOAJ |
| description | Assessing the severity level of dysarthria can provide an insight into the patient’s improvement, assist pathologists to plan therapy, and aid automatic dysarthric speech recognition systems. In this article, we present a comparative study on the classification of dysarthria severity levels using different deep learning techniques and acoustic features. First, we evaluate the basic architectural choices such as deep neural network (DNN), convolutional neural network, gated recurrent units and long short-term memory network using the basic speech features, namely, Mel-frequency cepstral coefficients (MFCCs) and constant-Q cepstral coefficients. Next, speech-disorder specific features computed from prosody, articulation, phonation and glottal functioning are evaluated on DNN models. Finally, we explore the utility of low-dimensional feature representation using subspace modeling to give i-vectors, which are then classified using DNN models. Evaluation is done using the standard UA-Speech and TORGO databases. By giving an accuracy of 93.97% under the speaker-dependent scenario and 49.22% under the speaker-independent scenario for the UA-Speech database, the DNN classifier using MFCC-based i-vectors outperforms other systems. |
| first_indexed | 2024-03-13T05:48:22Z |
| format | Article |
| id | doaj.art-f5833a587fb940579f70d5f0a5ead5e6 |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-13T05:48:22Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-f5833a587fb940579f70d5f0a5ead5e62023-06-13T20:06:27ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102022-01-01301147115710.1109/TNSRE.2022.31698149762324Automated Dysarthria Severity Classification: A Study on Acoustic Features and Deep Learning TechniquesAmlu Anna Joshy0https://orcid.org/0000-0001-9248-2841Rajeev Rajan1Electronics and Communication Engineering Department, College of Engineering Trivandrum, APJ Abdul Kalam Technological University, Thiruvananthapuram, IndiaDepartment of Computer Science and Engineering, Speech and Music Technology Laboratory, IIT Madras, Chennai, IndiaAssessing the severity level of dysarthria can provide an insight into the patient’s improvement, assist pathologists to plan therapy, and aid automatic dysarthric speech recognition systems. In this article, we present a comparative study on the classification of dysarthria severity levels using different deep learning techniques and acoustic features. First, we evaluate the basic architectural choices such as deep neural network (DNN), convolutional neural network, gated recurrent units and long short-term memory network using the basic speech features, namely, Mel-frequency cepstral coefficients (MFCCs) and constant-Q cepstral coefficients. Next, speech-disorder specific features computed from prosody, articulation, phonation and glottal functioning are evaluated on DNN models. Finally, we explore the utility of low-dimensional feature representation using subspace modeling to give i-vectors, which are then classified using DNN models. Evaluation is done using the standard UA-Speech and TORGO databases. By giving an accuracy of 93.97% under the speaker-dependent scenario and 49.22% under the speaker-independent scenario for the UA-Speech database, the DNN classifier using MFCC-based i-vectors outperforms other systems.https://ieeexplore.ieee.org/document/9762324/Deep learningdysarthriai-vectorsseverity assessment |
| spellingShingle | Amlu Anna Joshy Rajeev Rajan Automated Dysarthria Severity Classification: A Study on Acoustic Features and Deep Learning Techniques IEEE Transactions on Neural Systems and Rehabilitation Engineering Deep learning dysarthria i-vectors severity assessment |
| title | Automated Dysarthria Severity Classification: A Study on Acoustic Features and Deep Learning Techniques |
| title_full | Automated Dysarthria Severity Classification: A Study on Acoustic Features and Deep Learning Techniques |
| title_fullStr | Automated Dysarthria Severity Classification: A Study on Acoustic Features and Deep Learning Techniques |
| title_full_unstemmed | Automated Dysarthria Severity Classification: A Study on Acoustic Features and Deep Learning Techniques |
| title_short | Automated Dysarthria Severity Classification: A Study on Acoustic Features and Deep Learning Techniques |
| title_sort | automated dysarthria severity classification a study on acoustic features and deep learning techniques |
| topic | Deep learning dysarthria i-vectors severity assessment |
| url | https://ieeexplore.ieee.org/document/9762324/ |
| work_keys_str_mv | AT amluannajoshy automateddysarthriaseverityclassificationastudyonacousticfeaturesanddeeplearningtechniques AT rajeevrajan automateddysarthriaseverityclassificationastudyonacousticfeaturesanddeeplearningtechniques |