Abstract

Punctuation restoration is an important task in automatic speech recognition (ASR) which aim to restore the syntactic structure of generated ASR texts to improve readability. While punctuated texts are abundant from written documents, the discrepancy between written punctuated texts and ASR texts limits the usability of written texts in training punctuation restoration systems for ASR texts. This paper proposes a reinforcement learning method to exploit in-topic written texts and recent advances in large pre-trained generative language models to bridge this gap. The experiments show that our method achieves state-of-the-art performance on the ASR test set on two benchmark datasets for punctuation restoration.

Metadata

publication

arXiv preprint arXiv:2307.12949, 2023

year

2023

publication date

2023/7/24

authors

Viet Dac Lai, Abel Salinas, Hao Tan, Trung Bui, Quan Tran, Seunghyun Yoon, Hanieh Deilamsalehy, Franck Dernoncourt, Thien Huu Nguyen

link

https://arxiv.org/abs/2307.12949

resource_link

https://arxiv.org/pdf/2307.12949

journal

arXiv preprint arXiv:2307.12949