非自回归最小贝叶斯风险解码用于快速语音识别
Non-Autoregressive Minimum Bayes' Risk Decoding for Fast Speech Recognition
AI总结：
提出基于最小贝叶斯风险解码的非自回归解码框架，通过单次前向计算高效采样多个候选，在保持速度优势的同时提升识别性能。
摘要：
非自回归（NAR）解码并行生成输出令牌，使语音识别比自回归解码（从左到右顺序生成）更快。然而，由于NAR解码无法通过依赖先前生成的令牌来解决不确定性，识别性能会下降。为了解决这个问题，我们提出了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，它最大化从NAR模型输出概率中抽取的样本计算的期望效用，而不是最大化输出概率。值得注意的是，通过利用NAR模型的特性，单次前向计算即可高效获得多个样本。我们在LibriSpeech、Switchboard、AMI和网络演示语料库上的实验表明，我们的NAR-MBR解码优于先前的NAR解码，并且运行速度快于AR解码。
英文摘要：
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.
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。
