Non-autoregressive (NAR) decoding generates output tokens in parallel, making speech recognition faster than autoregressive decoding, which generates them sequentially from left to right. However, the recognition performance is degraded because NAR decoding cannot resolve uncertainty by conditioning on previously generated tokens. To address this issue, we propose a novel NAR decoding framework based on minimum Bayes' risk (MBR) decoding, termed NAR-MBR decoding, that maximizes the expected utility calculated from samples drawn from the output probability of an NAR model rather than maximizing the output probability. Notably, by leveraging the nature of NAR models, multiple samples are obtained efficiently with a single forward computation. Our experiments across LibriSpeech, Switchboard, AMI, and web presentation corpus demonstrated that our NAR-MBR decoding outperformed previous NAR decoding and ran faster than AR decoding.

翻译：非自回归（NAR）解码以并行方式生成输出标记，使得语音识别速度比从左到右依次生成的自回归解码更快。然而，由于NAR解码无法通过依赖先前生成的标记来消除不确定性，其识别性能有所下降。为解决此问题，我们提出一种基于最小贝叶斯风险（MBR）解码的新型NAR解码框架，称为NAR-MBR解码，该框架最大化从NAR模型输出概率中抽取样本计算得到的期望效用，而非最大化输出概率。值得注意的是，利用NAR模型的特性，通过单次前向计算即可高效获得多个样本。我们在LibriSpeech、Switchboard、AMI及网络演示语料库上的实验表明，所提出的NAR-MBR解码性能优于先前的NAR解码方法，且运行速度快于AR解码。