arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.03432cs.CLcs.LGcs.SDeess.AS
收藏

我们是WER,我们也是WER

WER we are and WER we think we are

Avaya Inc.(亚美亚公司);Wrocław University of Science and Technology(弗罗茨瓦夫科技大学);Johns Hopkins University(约翰斯·霍普金斯大学);Poznań University of Technology(波兹南理工大学)

Piotr Szymański, Piotr Żelasko, Mikolaj Morzy, Adrian Szymczak, Marzena Żyła-Hoppe, Joanna Banaszczak, Lukasz Augustyniak, Jan Mizgajski, Yishay Carmiel

摘要:

会话语音的自然语言处理需要高质量的转录本。在本文中,我们表达了我们的怀疑对最近的报告非常低的字出错率(WER)实现的现代自动语音识别(ASR)系统的基准数据集。我们概述了流行的基准测试的几个问题,并比较了三个国家的最先进的商业ASR系统的内部数据集的真实生活中自发的人类对话和HUB'05公共基准。我们发现,WERs显着高于最好的报告结果。我们制定了一套指南,可以帮助创建具有高质量注释的真实多域数据集,用于训练和测试强大的ASR系统。

英文摘要:

Natural language processing of conversational speech requires the availability of high-quality transcripts. In this paper, we express our skepticism towards the recent reports of very low Word Error Rates (WERs) achieved by modern Automatic Speech Recognition (ASR) systems on benchmark datasets. We outline several problems with popular benchmarks and compare three state-of-the-art commercial ASR systems on an internal dataset of real-life spontaneous human conversations and HUB'05 public benchmark. We show that WERs are significantly higher than the best reported results. We formulate a set of guidelines which may aid in the creation of real-life, multi-domain datasets with high quality annotations for training and testing of robust ASR systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑