arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2204.05617cs.CLcs.AI
收藏

德语中的ASR:详细的错误分析

ASR in German: A Detailed Error Analysis

Hof University of Applied Sciences(霍夫应用科学大学)

Johannes Wirth, Rene Peinl

摘要:

基于神经网络的自动语音识别(ASR)的免费可用系统的数量正在稳步增长,预测的可靠性也在不断提高。然而,对训练模型的评估通常仅基于诸如WER或CER的统计度量,其不提供对当从语音输入预测转录本时所产生的错误的性质或影响的任何洞察。这项工作提出了一系列ASR模型架构,这些架构在德语上进行了预训练,并在不同测试数据集的基准上对其进行了评估。它识别跨架构的预测错误,将其分类,并将每个类别的错误源追溯到训练数据以及其他来源。最后,它讨论了解决方案,以创建质量更好的训练数据集和更强大的ASR系统。

英文摘要:

The amount of freely available systems for automatic speech recognition (ASR) based on neural networks is growing steadily, with equally increasingly reliable predictions. However, the evaluation of trained models is typically exclusively based on statistical metrics such as WER or CER, which do not provide any insight into the nature or impact of the errors produced when predicting transcripts from speech input. This work presents a selection of ASR model architectures that are pretrained on the German language and evaluates them on a benchmark of diverse test datasets. It identifies cross-architectural prediction errors, classifies those into categories and traces the sources of errors per category back into training data as well as other sources. Finally, it discusses solutions in order to create qualitatively better training datasets and more 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。

↑