Guided contrastive self-supervised pre-training for automatic speech recognition

Autor:	Khare, Aparna, Wu, Minhua, Bhati, Saurabhchand, Droppo, Jasha, Maas, Roland
Rok vydání:	2022
Předmět:	Computer Science - Computation and Language Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
DOI:	10.1109/SLT54892.2023.10022676
Popis:	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. Comment: To appear in SLT 2022
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2210.12335 Zobrazit plný text záznamu View this record from Arxiv