Contrastive Semi-supervised Learning for ASR

Abstract

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% compared to the standard Cross-Entropy pseudo-labeling (CE-PL) when 10hr of supervised data is used to annotate 75,000hr of videos. The WER reduction jumps to 19% under the ultra low-resource condition of using 1hr labels for teacher supervision. CSL generalizes much better in out-of-domain conditions, showing up to 17% WER reduction compared to the best CE-PL pre-trained model.

References in corpus (10)

• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• Do Deep Nets Really Need to be Deep?
• Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders
• Transformer-based Acoustic Modeling for Hybrid Speech Recognition
• Improved Noisy Student Training for Automatic Speech Recognition
• Self-Training for End-to-End Speech Recognition
• End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
• Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition
• Effectiveness of self-supervised pre-training for speech recognition