论文标题
两个头大于一个：一种两阶段的方法，用于降低复杂域的单声道降噪方法
Two Heads Are Better Than One: A Two-Stage Approach for Monaural Noise Reduction in the Complex Domain
论文作者
论文摘要
在低信噪比条件下，很难同时有效地恢复大小和相位信息。为了解决这个问题，本文提出了一种两阶段算法，以使联合优化问题W.R.T.大小和相位分为两个子任务。在第一阶段，仅优化了幅度，该幅度结合了嘈杂的相，以获得粗糙的复杂的清洁语音频谱估计。在第二阶段，大小和相分量都得到了完善。实验是在WSJ0-SI84语料库上进行的，结果表明，所提出的方法在PESQ，ESTOI和SDR方面显着优于先前的基准。
In low signal-to-noise ratio conditions, it is difficult to effectively recover the magnitude and phase information simultaneously. To address this problem, this paper proposes a two-stage algorithm to decouple the joint optimization problem w.r.t. magnitude and phase into two sub-tasks. In the first stage, only magnitude is optimized, which incorporates noisy phase to obtain a coarse complex clean speech spectrum estimation. In the second stage, both the magnitude and phase components are refined. The experiments are conducted on the WSJ0-SI84 corpus, and the results show that the proposed approach significantly outperforms previous baselines in terms of PESQ, ESTOI, and SDR.
