TL;DR本研究提出了一种新的混淆感知的微调方法,以减轻 ASR 误差对已预训练的语言模型产生的影响,并在 ATIS 数据集上进行了实验,结果表明该方法显著提高了 ASR 转录文本上口语理解的性能。
Abstract
Employing pre-trained language models (LM) to extract contextualized word
representations has achieved state-of-the-art performance on various NLP tasks.
However, applying this technique to noisy transcripts generated by automatic
speech recognizer (ASR) is concerned. Therefore, this p