Unleashing Effective Identification of ALS Based on Vowel Phonation: A Deep Learning Approach

Amyotrophic Lateral Sclerosis Mel-Frequency Cepstral Coefficients CNN LSTM Dilation Rate Classification Minsk2020 Vowel Phonation

Authors

Downloads

ALS (Amyotrophic Lateral Sclerosis) is one of the fatal diseases across the world. Therefore, early detection can save patients suffering from ALS from life-threatening consequences. Typically, ALS can be identified based on different factors, and one such factor is voice analysis. Detection of ALS using sound signals is convenient and simpler than other methods, as it is a non-invasive approach, which makes the process faster and more efficient for detection. However, detection of ALS using traditional approaches is challenging, as it is a time-consuming process and heavy reliance on medical experts is needed. Therefore, AI-based models can be used for effective classification of ALS and non-ALS patients, as AI-based models possess the immense ability to examine vast amounts of data, including audio files, effectively. Owing to these factors, the proposed model focuses on employing an AI-based model for ALS classification based on vowel phonation /a/ and /i/. The process is carried out using the Minsk2020 dataset, where important features needed for the proposed model are extracted using MFCC (Mel-frequency cepstral coefficients) by removing the shakiness and jitteriness of the voice. The MFCC feature extraction technique extracts features based on the mel scale, as this reflects human auditory perception, thereby extracting features that are useful for classification. These extracted features are fed to CNN-LSTM (Convolutional Neural Network – Long Short Term Memory) with rapid dilatenet for classifying ALS and non-ALS patients accurately by identifying even the subtle changes in audio signals using maximizing the expansion/dilation rate and aid the context information for interpreting and analyzing the sound of vowels accurately and correctly without any loss of information. Finally, the efficacy of the proposed model is assessed using evaluation metrics. The proposed research work can assist medical professionals in detecting patients with ALS based on vowel phonation.