从过去的错误中学习：通过噪声干净的短语上下文建模改进自动语音识别输出
Learning from Past Mistakes: Improving Automatic Speech Recognition Output via Noisy-Clean Phrase Context Modeling
摘要：
自动语音识别（ASR）系统经常由于子系统修剪（声学、语言和发音模型）而产生不可恢复的错误;例如，在基于语言学用长期上下文重新评分之前，由于使用短期上下文的声学而修剪单词。在这项工作中，我们建模ASR作为一个基于短语的嘈杂的变换通道，并提出了一个纠错系统，可以从所有独立的模块组成的ASR的聚合错误，并试图反转这些。所提出的系统可以使用神经网络语言模型来利用长期上下文，并且可以更好地在现有ASR输出可能性之间进行选择，以及重新引入先前修剪的或看不见的（词汇表外的）短语。它在性能不佳的ASR条件下提供校正，而不会降低任何准确的transmittance;这种校正在域外和不匹配的数据ASR上更大。我们的系统始终如一地提供了对基线ASR的改进，即使基线通过递归神经网络语言模型重新评分进一步优化。这表明，任何ASR改进都可以独立利用，并且我们提出的系统仍然可以为高度优化的ASR提供好处。最后，我们提出了一个广泛的分析，我们的系统纠正的错误类型。
英文摘要：
Automatic speech recognition (ASR) systems often make unrecoverable errors due to subsystem pruning (acoustic, language and pronunciation models); for example pruning words due to acoustics using short-term context, prior to rescoring with long-term context based on linguistics. In this work we model ASR as a phrase-based noisy transformation channel and propose an error correction system that can learn from the aggregate errors of all the independent modules constituting the ASR and attempt to invert those. The proposed system can exploit long-term context using a neural network language model and can better choose between existing ASR output possibilities as well as re-introduce previously pruned or unseen (out-of-vocabulary) phrases. It provides corrections under poorly performing ASR conditions without degrading any accurate transcriptions; such corrections are greater on top of out-of-domain and mismatched data ASR. Our system consistently provides improvements over the baseline ASR, even when baseline is further optimized through recurrent neural network language model rescoring. This demonstrates that any ASR improvements can be exploited independently and that our proposed system can potentially still provide benefits on highly optimized ASR. Finally, we present an extensive analysis of the type of errors corrected by our system.
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。
