Contrastive Semi-supervised Learning for ASR
share
Pseudo-labeling is the most adopted method for pre-training automatic speech recognition (ASR) models. However, its performance suffers from the supervised teacher model's degrading quality in low-resource setups and under domain transfer. Inspired by the successes of contrastive representation learning for computer vision and speech applications, and more recently for supervised learning of visual objects, we propose Contrastive Semi-supervised Learning (CSL). CSL eschews directly predicting teacher-generated pseudo-labels in favor of utilizing them to select positive and negative examples. In the challenging task of transcribing public social media videos, using CSL reduces the WER by 8 supervised data is used to annotate 75,000hr of videos. The WER reduction jumps to 19 supervision. CSL generalizes much better in out-of-domain conditions, showing up to 17
READ FULL TEXT