迭代自回归：一种提升低延迟语音增强模型的新技巧
Iterative autoregression: a novel trick to improve your low-latency speech enhancement model
AI总结：
本文针对低延迟流式语音增强中教师强制训练导致的训练推理不匹配问题，提出一种迭代自回归训练方法，并在多种架构和训练场景下验证了其稳定提升效果。
摘要：
流式模型是实时语音增强工具的重要组成部分。流式机制限制了语音增强模型只能使用极少的未来信息上下文。因此，低延迟流式设置通常被认为是一项具有挑战性的任务，并对模型质量产生显著的负面影响。然而，流式生成的顺序特性为自回归提供了自然的可能性，即在生成当前预测时利用先前的预测结果。训练自回归模型的传统方法是教师强制，但其主要缺点在于训练与推理之间的不匹配，可能导致质量大幅下降。在本研究中，我们提出了一种简单而有效的替代技术，用于训练自回归低延迟语音增强模型。我们证明，所提出的方法能够在不同的架构和训练场景中带来稳定的性能提升。
英文摘要：
Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is generally considered a challenging task and has a significant negative impact on the model's quality. However, the sequential nature of streaming generation offers a natural possibility for autoregression, that is, utilizing previous predictions while making current ones. The conventional method for training autoregressive models is teacher forcing, but its primary drawback lies in the training-inference mismatch that can lead to a substantial degradation in quality. In this study, we propose a straightforward yet effective alternative technique for training autoregressive low-latency speech enhancement models. We demonstrate that the proposed approach leads to stable improvement across diverse architectures and training scenarios.
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。
