RED-ACE: Robust Error Detection for ASR using Confidence Embeddings
RED-ACE: Robust Error Detection for ASR using Confidence Embeddings
复制标题
DOI：
10.48550/arxiv.2203.07172
复制
发表时间：
2022-03
期刊：
影响因子：
--
通讯作者：
Zorik Gekhman;Dina Zverinski;Jonathan Mallinson;Genady Beryozkin
中科院分区：
文献类型：
--
作者：
Zorik Gekhman;Dina Zverinski;Jonathan Mallinson;Genady Beryozkin
自动语音识别（ASR）错误检测（AED）模型旨在对自动语音识别（ASR）系统的输出进行后处理，以检测转录错误。现代方法通常使用基于文本的输入，仅由ASR转录假设组成，忽略了来自ASR模型的附加信号。相反，我们利用ASR系统的单词级置信度评分来提高AED的性能。具体来说，我们在AED模型的编码器中添加了一个ASR置信度嵌入（ACE）层，允许我们将置信度分数和转录文本联合编码为上下文化表示。我们的实验显示了ASR置信度评分对AED的好处，它们对文本信号的互补效应，以及ACE结合这些信号的有效性和鲁棒性。为了促进进一步的研究，我们发布了一个新的AED数据集，该数据集由librisspeech语料库上的ASR输出组成，并附有注释的转录错误。
ASR Error Detection (AED) models aim to post-process the output of Automatic Speech Recognition (ASR) systems, in order to detect transcription errors. Modern approaches usually use text-based input, comprised solely of the ASR transcription hypothesis, disregarding additional signals from the ASR model. Instead, we utilize the ASR system’s word-level confidence scores for improving AED performance. Specifically, we add an ASR Confidence Embedding (ACE) layer to the AED model’s encoder, allowing us to jointly encode the confidence scores and the transcribed text into a contextualized representation. Our experiments show the benefits of ASR confidence scores for AED, their complementary effect over the textual signal, as well as the effectiveness and robustness of ACE for combining these signals. To foster further research, we publish a novel AED dataset consisting of ASR outputs on the LibriSpeech corpus with annotated transcription errors.