语音识别系统错误修正的开放挑战（CS CL）

• 2020 年 1 月 14 日
• 筆記

本文提出了提高语音自动识别系统性能的长期挑战。这项挑战的目标是研究如何在语音处理系统先前错误的基础上修正识别结果。描述了为该任务准备的数据集，并给出了评价标准。

原文题目：Open Challenge for Correcting Errors of Speech Recognition Systems

原文：The paper announces the new long-term challenge for improving the performance of automatic speech recognition systems. The goal of the challenge is to investigate methods of correcting the recognition results on the basis of previously made errors by the speech processing system. The dataset prepared for the task is described and evaluation criteria are presented.

原文作者：Marek Kubis,Zygmunt Vetulani,Mikołaj Wypych,Tomasz Ziętkiewicz

原文地址：https://arxiv.org/abs/2001.03041