Repackagingaugment: Overcoming Prediction Error Amplification in Weight-Averaged Speech Recognition Models Subject to Self-Training - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

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]

This author has not been identified. Look up 'Jae Hong Lee' in GoogleThis author has not been identified. Look up 'Dong-hyun Kim' in GoogleThis author has not been identified. Look up 'Joon-Hyuk Chang' in Google

runs on WebDSL