Jae Hong Lee, Dong-hyun Kim, Joon-Hyuk Chang. Repackagingaugment: Overcoming Prediction Error Amplification in Weight-Averaged Speech Recognition Models Subject to Self-Training. In IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023. pages 1-5, IEEE, 2023. [doi]
Abstract is missing.