基于Conformer Metric GAN的无约束全局相位偏置感知单通道语音增强
Unrestricted Global Phase Bias-Aware Single-channel Speech Enhancement with Conformer-based Metric GAN
AI总结：
针对神经网络增强相位谱效果不佳的问题，提出允许全局相位偏置的相位重建优化方法，应用于CMGAN基线模型，在无额外计算开销下实现了最先进的单通道语音增强性能。
摘要：
近年来神经网络快速发展，单通道语音增强领域中各种网络增强含噪语音幅度谱的能力已变得极其出色。然而，使用神经网络增强相位谱通常效果不佳，这仍是一个具有挑战性的问题。在本文中，我们发现人耳无法敏感地感知精确相位谱与偏置相位（BP）谱之间的差异。因此，我们提出了一种相位重建的优化方法，允许全局相位偏置上的自由，而不是重建精确的相位谱。我们将其应用于基于Conformer的度量生成对抗网络（CMGAN）基线模型，该方法放宽了现有精确相位的约束，并赋予神经网络更广阔的学习空间。结果表明，该方法在不产生额外计算开销的情况下，实现了新的最先进性能。
英文摘要：
With the rapid development of neural networks in recent years, the ability of various networks to enhance the magnitude spectrum of noisy speech in the single-channel speech enhancement domain has become exceptionally outstanding. However, enhancing the phase spectrum using neural networks is often ineffective, which remains a challenging problem. In this paper, we found that the human ear cannot sensitively perceive the difference between a precise phase spectrum and a biased phase (BP) spectrum. Therefore, we propose an optimization method of phase reconstruction, allowing freedom on the global-phase bias instead of reconstructing the precise phase spectrum. We applied it to a Conformer-based Metric Generative Adversarial Networks (CMGAN) baseline model, which relaxes the existing constraints of precise phase and gives the neural network a broader learning space. Results show that this method achieves a new state-of-the-art performance without incurring additional computational overhead.
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。
