Voice based classification of patients with Amyotrophic Lateral Sclerosis, Parkinson’s Disease and Healthy Controls with CNN-LSTM using transfer learning

Mallela, Jhansi; Illa, Aravind; B, Suhas; Udupa, Sathvik; Nalini, Atchayaram; Yadav, Ravi; Reddy, P. Vijayapal; Gope, Dipanjan; Ghosh, Prasanta Kumar

doi:10.1109/icassp40776.2020.9053682

Cited by 18 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A CNN-LSTM based deep neural network classifier, following [11], is adapted in this work. ALS and PD affect the paralinguistic characteristics of speech in a suprasegmental level.…”

Section: Classifiermentioning

confidence: 99%

“…Deep neural network (DNN) based classifiers can exploit the information present in these cues to perform the classification with high degree of accuracy. Mel frequency cepstral coefficients (MFCC), representative of spectral characteristics and articulation, has been widely used for this purpose [10,11,12]. Suhas et al [10] employed dense neural network to perform the classification, whereas Mallela et al [11] explored 1D-convolutional neural network (CNN) and long short term memory (LSTM) based classifier using transfer learning approach.…”

Section: Introductionmentioning

confidence: 99%

“…Mel frequency cepstral coefficients (MFCC), representative of spectral characteristics and articulation, has been widely used for this purpose [10,11,12]. Suhas et al [10] employed dense neural network to perform the classification, whereas Mallela et al [11] explored 1D-convolutional neural network (CNN) and long short term memory (LSTM) based classifier using transfer learning approach. Log Mel spectrograms have been found to perform better than MFCC in the context of 2D-CNN based automatic classification and severity prediction of ALS and PD [13].…”

Section: Introductionmentioning

confidence: 99%

“…Pitch, on the other hand, has not been explicitly used as a feature of speech in this context, though it has been reported to get affected as a prosodic component of speech in these diseases [16,17]. We experiment with these two speech cues using CNN-LSTM classifier [11] of three different levels of complexity at four different signal-to-noise ratio (SNR) conditions. Though MFCC is proven to perform well in literature, it is high dimensional and prone to alter in additive noise conditions.…”

Section: Introductionmentioning

confidence: 99%

“…The subjects were given a few minutes of preparation time before they started. Four different speech tasks namely spontaneous speech, sustained phoneme production, diadochokinetic task and image description task have been considered in literature[10,11,15]. However, in this work we consider only spontaneous speech since pitch modulation during this Gender and age details of subjects…”

mentioning

confidence: 99%

See 4 more Smart Citations

Effect of Noise and Model Complexity on Detection of Amyotrophic Lateral Sclerosis and Parkinson’s Disease Using Pitch and MFCC

Bhattacharjee

Mallela

Atchayarcmf

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Dysarthria due to Amyotrophic Lateral Sclerosis (ALS) and Parkinson's disease (PD) impacts both articulation and prosody in an individual's speech. Complex deep neural networks exploit these cues for detection of ALS and PD. These are typically done using recordings in laboratory condition. This study aims to examine the robustness of these cues against background noise and model complexity, which has not been investigated before. We perform classification experiments with pitch and Mel-frequency cepstral coefficients (MFCC) using models of three different complexities and additive white Gaussian noise in four signal-to-noise-ratio (SNR) conditions. The findings are as follows: 1) In clean condition, pitch performs similar to MFCC across most model complexities considered, suggesting that one-dimensional pitch pattern provides discriminative cues for the classification to an extent equal to that of multi-dimensional MFCC, 2) Similar trend is observed in noisy cases when classifiers are trained and tested in matched noise and SNR conditions, 3) When the classifiers trained on clean data are applied in noisy cases, pitch based average classification accuracies are found to be 20.09% and 24.73% higher than those using MFCC for ALS vs. healthy and PD vs. healthy, respectively, suggesting robustness of pitch based classifier against noise and model complexity.

show abstract

“…A CNN-LSTM based deep neural network classifier, following [11], is adapted in this work. ALS and PD affect the paralinguistic characteristics of speech in a suprasegmental level.…”

Section: Classifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%