Picture for Sudarsana Reddy Kadiri

Sudarsana Reddy Kadiri

MMSD-Net: Towards Multi-modal Stuttering Detection

Add code
Jul 16, 2024
Viaarxiv icon

Wav2vec-based Detection and Severity Level Classification of Dysarthria from Speech

Add code
Sep 25, 2023
Viaarxiv icon

Analysis and Detection of Pathological Voice using Glottal Source Features

Add code
Sep 25, 2023
Viaarxiv icon

Time-Varying Quasi-Closed-Phase Analysis for Accurate Formant Tracking in Speech Signals

Add code
Aug 31, 2023
Figure 1 for Time-Varying Quasi-Closed-Phase Analysis for Accurate Formant Tracking in Speech Signals
Figure 2 for Time-Varying Quasi-Closed-Phase Analysis for Accurate Formant Tracking in Speech Signals
Figure 3 for Time-Varying Quasi-Closed-Phase Analysis for Accurate Formant Tracking in Speech Signals
Figure 4 for Time-Varying Quasi-Closed-Phase Analysis for Accurate Formant Tracking in Speech Signals
Viaarxiv icon

Severity Classification of Parkinson's Disease from Speech using Single Frequency Filtering-based Features

Add code
Aug 17, 2023
Figure 1 for Severity Classification of Parkinson's Disease from Speech using Single Frequency Filtering-based Features
Figure 2 for Severity Classification of Parkinson's Disease from Speech using Single Frequency Filtering-based Features
Figure 3 for Severity Classification of Parkinson's Disease from Speech using Single Frequency Filtering-based Features
Figure 4 for Severity Classification of Parkinson's Disease from Speech using Single Frequency Filtering-based Features
Viaarxiv icon

Refining a Deep Learning-based Formant Tracker using Linear Prediction Methods

Add code
Aug 17, 2023
Viaarxiv icon

Investigation of Self-supervised Pre-trained Models for Classification of Voice Quality from Speech and Neck Surface Accelerometer Signals

Add code
Aug 06, 2023
Figure 1 for Investigation of Self-supervised Pre-trained Models for Classification of Voice Quality from Speech and Neck Surface Accelerometer Signals
Figure 2 for Investigation of Self-supervised Pre-trained Models for Classification of Voice Quality from Speech and Neck Surface Accelerometer Signals
Figure 3 for Investigation of Self-supervised Pre-trained Models for Classification of Voice Quality from Speech and Neck Surface Accelerometer Signals
Figure 4 for Investigation of Self-supervised Pre-trained Models for Classification of Voice Quality from Speech and Neck Surface Accelerometer Signals
Viaarxiv icon

End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks

Add code
Oct 28, 2022
Figure 1 for End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks
Figure 2 for End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks
Figure 3 for End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks
Figure 4 for End-to-end Ensemble-based Feature Selection for Paralinguistics Tasks
Viaarxiv icon

Formant Tracking Using Quasi-Closed Phase Forward-Backward Linear Prediction Analysis and Deep Neural Networks

Add code
Jan 05, 2022
Figure 1 for Formant Tracking Using Quasi-Closed Phase Forward-Backward Linear Prediction Analysis and Deep Neural Networks
Figure 2 for Formant Tracking Using Quasi-Closed Phase Forward-Backward Linear Prediction Analysis and Deep Neural Networks
Figure 3 for Formant Tracking Using Quasi-Closed Phase Forward-Backward Linear Prediction Analysis and Deep Neural Networks
Figure 4 for Formant Tracking Using Quasi-Closed Phase Forward-Backward Linear Prediction Analysis and Deep Neural Networks
Viaarxiv icon

Aalto's End-to-End DNN systems for the INTERSPEECH 2020 Computational Paralinguistics Challenge

Add code
Aug 06, 2020
Figure 1 for Aalto's End-to-End DNN systems for the INTERSPEECH 2020 Computational Paralinguistics Challenge
Figure 2 for Aalto's End-to-End DNN systems for the INTERSPEECH 2020 Computational Paralinguistics Challenge
Figure 3 for Aalto's End-to-End DNN systems for the INTERSPEECH 2020 Computational Paralinguistics Challenge
Figure 4 for Aalto's End-to-End DNN systems for the INTERSPEECH 2020 Computational Paralinguistics Challenge
Viaarxiv icon