 ValSub: Subsampling Validation Data to Mitigate Forgetting during ASR PersonalizationIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025 |
 Continuously Learning New Words in Automatic Speech RecognitionIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024 |
 Continual Learning for On-Device Speech Recognition using Disentangled
ConformersIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 |
 Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic
Forgetting in Automatic Speech RecognitionIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022 |
 Damage Control During Domain Adaptation for Transducer Based Automatic
Speech RecognitionSpoken Language Technology Workshop (SLT), 2022 |
