TL;DR
This paper enhances punctuation restoration in speech recognition by integrating external POS tags and a novel sequence boundary sampling method, achieving state-of-the-art results on the IWSLT benchmark.
Contribution
It introduces a method to fuse external POS tags into language models and proposes sequence boundary sampling for improved punctuation prediction.
Findings
Consistent performance improvements over previous methods
Achieves new state-of-the-art on IWSLT benchmark
Both large language models and POS tags are crucial for performance
Abstract
Punctuation restoration is an important post-processing step in automatic speech recognition. Among other kinds of external information, part-of-speech (POS) taggers provide informative tags, suggesting each input token's syntactic role, which has been shown to be beneficial for the punctuation restoration task. In this work, we incorporate an external POS tagger and fuse its predicted labels into the existing language model to provide syntactic information. Besides, we propose sequence boundary sampling (SBS) to learn punctuation positions more efficiently as a sequence tagging task. Experimental results show that our methods can consistently obtain performance gains and achieve a new state-of-the-art on the common IWSLT benchmark. Further ablation studies illustrate that both large pre-trained language models and the external POS tagger take essential parts to improve the model's…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
