Guided contrastive self-supervised pre-training for automatic speech recognition
Khare, Aparna, Wu, Minhua, Bhati, Saurabhchand, Droppo, Jasha, Maas, Roland
–arXiv.org Artificial Intelligence
Contrastive Predictive Coding (CPC) is a representation learning method that maximizes the mutual information between intermediate latent representations and the output of a given model. It can be used to effectively initialize the encoder of an Automatic Speech Recognition (ASR) model. We present a novel modification of CPC called Guided Contrastive Predictive Coding (GCPC). Our proposed method maximizes the mutual information between representations from a prior-knowledge model and the output of the model being pre-trained, allowing prior knowledge injection during pre-training. We validate our method on 3 ASR tasks: German, French and English. Our method outperforms CPC pre-training on all three datasets, reducing the Word Error Rate (WER) by 4.44%, 6.55% and 15.43% relative on the German, French and English (Librispeech) tasks respectively, compared to training from scratch, while CPC pre-training only brings 2.96%, 1.01% and 14.39% relative WER reduction respectively.
arXiv.org Artificial Intelligence
Oct-21-2022
- Country:
- South America > Chile
- North America
- United States (0.04)
- Canada > Quebec
- Montreal (0.04)
- Genre:
- Research Report (1.00)
- Technology: