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 2406.07589cs.CLcs.AI
收藏

标注并纠正:一种用于纠正语音识别错误的高精度译后编辑方法

Tag and correct: high precision post-editing approach to correction of speech recognition errors

Adam Mickiewicz University in Poznań(波兹南密茨凯维奇大学);Samsung R&D Institute Poland(三星波兰研发研究院)

Tomasz Ziętkiewicz

AI总结:

本文提出“标注并纠正”的 ASR 译后编辑方法,通过神经序列标注器逐词定位并纠正错误,以较少训练资源达到与既有方法相当的性能,并实现高精度、低延迟的工业级纠错。

摘要:

本文提出了一种通过译后编辑来纠正语音识别错误的新方法。该方法包含一个神经序列标注器和一个纠正模块:前者学习如何逐词纠正 ASR(自动语音识别)假设,后者则应用标注器返回的纠正结果。所提出的解决方案适用于任何 ASR 系统,而不受其架构限制,并能对正在纠正的错误提供高精度控制。这在生产环境中尤为关键,因为在这些环境中,避免纠错模型引入新错误可能比整体结果的净收益更加重要。结果表明,所提出的纠错模型的性能与以往方法相当,同时训练所需资源少得多,这使其适合工业应用;在工业应用中,推理延迟和训练时间都是限制其他技术使用的关键因素。

英文摘要:

This paper presents a new approach to the problem of correcting speech recognition errors by means of post-editing. It consists of using a neural sequence tagger that learns how to correct an ASR (Automatic Speech Recognition) hypothesis word by word and a corrector module that applies corrections returned by the tagger. The proposed solution is applicable to any ASR system, regardless of its architecture, and provides high-precision control over errors being corrected. This is especially crucial in production environments, where avoiding the introduction of new mistakes by the error correction model may be more important than the net gain in overall results. The results show that the performance of the proposed error correction models is comparable with previous approaches while requiring much smaller resources to train, which makes it suitable for industrial applications, where both inference latency and training times are critical factors that limit the use of other techniques.

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。

↑