Semi-Supervised Learning with Data Augmentation for End-to-End ASR

no code implementations • 27 Jul 2020 • Felix Weninger, Franco Mana, Roberto Gemello, Jesús Andrés-Ferrer, Puming Zhan

In the result, the Noisy Student algorithm with soft labels and consistency regularization achieves 10. 4% word error rate (WER) reduction when adding 475h of unlabeled data, corresponding to a recovery rate of 92%.

Data Augmentation Image Classification +1