用短语重写提升语音识别后处理效率，省计算又保精度。
Predicting Compact Phrasal Rewrites with Large Language Models for ASR Post Editing
- 提出仅保留目标短语的编辑表示法，压缩输出长度。
- 在LibriSpeech上减少50%-60%的错误率差距，仅损失10%-20%压缩率。
- 适合追求高效部署的语音识别后处理场景。
大型语言模型在文本风格转换和语法纠错等重写任务中表现优异。尽管输入与输出间存在大量重叠，但解码开销仍随输出长度增加而上升。Kaneko与Okazaki（2023）提出一种与模型无关的编辑跨度表示法，通过利用输入输出重叠压缩重写内容，在四项重写任务中实现近80%的输出长度降低，且准确率影响极小。本文受短语统计机器翻译启发，提出替代性的短语级编辑表示法，并系统比较其与跨度表示法的性能。将该方法应用于自动语音识别（ASR）后处理任务，结果表明，仅保留目标短语的编辑表示法在效率与准确率之间达到最佳平衡。在LibriSpeech测试集上，该方法使编辑跨度模型与完整重写模型之间的词错误率差距缩小了50%-60%，同时仅损失编辑跨度模型10%-20%的长度压缩率。
原文摘要 · Abstract (English)
Large Language Models (LLMs) excel at rewriting tasks such as text style transfer and grammatical error correction. While there is considerable overlap between the inputs and outputs in these tasks, the decoding cost still increases with output length, regardless of the amount of overlap. By leveraging the overlap between the input and the output, Kaneko and Okazaki (2023) proposed model-agnostic edit span representations to compress the rewrites to save computation. They reported an output length reduction rate of nearly 80% with minimal accuracy impact in four rewriting tasks. In this paper, we propose alternative edit phrase representations inspired by phrase-based statistical machine translation. We systematically compare our phrasal representations with their span representations. We apply the LLM rewriting model to the task of Automatic Speech Recognition (ASR) post editing and show that our target-phrase-only edit representation has the best efficiency-accuracy trade-off. On the LibriSpeech test set, our method closes 50-60% of the WER gap between the edit span model and the full rewrite model while losing only 10-20% of the length reduction rate of the edit span model.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。