arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.09249eess.AScs.SD
收藏

实时深度噪声抑制的有效模型

Towards efficient models for real-time deep noise suppression

Microsoft Research(微软研究院)

Sebastian Braun, Hannes Gamper, Chandan K. A. Reddy, Ivan Tashev

摘要:

随着最近的研究进展,深度学习模型正在成为实时应用中语音增强的有吸引力和强大的选择。虽然最先进的模型可以在语音质量和背景噪声降低方面取得出色的效果,但主要的挑战是获得足够紧凑的模型,这些模型在推理时间内具有资源效率。数据驱动方法的一个重要但经常被忽视的方面是,只有在真实数据上进行测试并使用有用的指标进行评估时,结果才能令人信服。在这项工作中,我们研究了用于语音增强的合理的小递归和卷积递归网络架构,并在考虑混响的大型数据集上进行了训练。我们表现出有趣的计算复杂性和可实现的语音质量之间的权衡,测量使用一个高度准确的MOS估计的真实录音。结果表明,可实现的语音质量是网络复杂度的函数,并显示哪些模型有更好的权衡。

英文摘要:

With recent research advancements, deep learning models are becoming attractive and powerful choices for speech enhancement in real-time applications. While state-of-the-art models can achieve outstanding results in terms of speech quality and background noise reduction, the main challenge is to obtain compact enough models, which are resource efficient during inference time. An important but often neglected aspect for data-driven methods is that results can be only convincing when tested on real-world data and evaluated with useful metrics. In this work, we investigate reasonably small recurrent and convolutional-recurrent network architectures for speech enhancement, trained on a large dataset considering also reverberation. We show interesting tradeoffs between computational complexity and the achievable speech quality, measured on real recordings using a highly accurate MOS estimator. It is shown that the achievable speech quality is a function of network complexity, and show which models have better tradeoffs.

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。

↑