https://arxiv.org/abs/2010.10504
Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition (Yu Zhang, James Qin, Daniel S. Park, Wei Han, Chung-Cheng Chiu, Ruoming Pang, Quoc V. Le, Yonghui Wu)
wav2vec 프리트레이닝 + noisy student semi supervision + 1 빌리언 파라미터 conformer로 librispeech test/test-other wer 1.4%/2.6% 달성!
#semi_supervised_learning #asr #pretraining