 LipGER: Visually-Conditioned Generative Error Correction for Robust
Automatic Speech RecognitionInterspeech (Interspeech), 2024 |
 Model Inversion Robustness: Can Transfer Learning Help?Computer Vision and Pattern Recognition (CVPR), 2024 |
 Wav2code: Restore Clean Speech Representations via Codebook Lookup for
Noise-Robust ASRIEEE/ACM Transactions on Audio Speech and Language Processing (TASLP), 2023 |
 Generating EEG features from Acoustic featuresEuropean Signal Processing Conference (EUSIPCO), 2020 |
 Speech Synthesis using EEGIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020 |
 Advancing Speech Recognition With No Speech Or With Noisy SpeechEuropean Signal Processing Conference (EUSIPCO), 2019 |
 Robust End-to-End Speaker Verification Using EEGEuropean Signal Processing Conference (EUSIPCO), 2019 |
