publications
2025
- arXiv
Joint Learning using Mixture-of-Expert-Based Representation for Enhanced Speech Generation and Robust Emotion RecognitionarXiv preprint arXiv:2509.08470, 2025 - ICASSP
Mask Augmentation For Tumor Classification In Medical ImagesIn IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025 - ICASSP
Noise-Robust Speech Emotion Recognition Using Shared Self-Supervised Representations with Integrated Speech EnhancementIn IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025 - ICASSP
Valve Token Masked Autoencoder for Missing Recordings on Cardiac Abnormality ClassificationIn IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025
2024
- npj Prim.The unreliability of crackles: insights from a breath sound study using physicians and artificial intelligencenpj Primary Care Respiratory Medicine, 2024
- ICASSP
GaP-Aug: Gamma Patch-Wise Correction Augmentation Method for Respiratory Sound ClassificationIn IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024