研究人员开发了一种新的语音识别非自回归解码框架，称为NAR-MBR解码。该方法旨在通过并行生成输出令牌来提高语音识别的速度，克服了非自回归模型通常伴随的性能下降。通过最大化从样本中获得的预期效用，而不是直接概率，NAR-MBR解码实现了更快的处理速度，并在多个基准数据集上优于以前的非自回归方法。 AI
影响 这项研究为语音识别提供了一种更快、可能更准确的方法，这将有利于实时应用程序。
排序理由 该集群包含一篇详细介绍语音识别新研究方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.17537v1 Announce Type: cross Abstract: 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 de…
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 uncerta…