arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1911.04697cs.SDeess.AS
收藏

PHASEN:一种相位和谐波感知的语音增强网络

PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network

University of Science and Technology of China(中国科学技术大学);Microsoft Research Asia(微软亚洲研究院)

Dacheng Yin, Chong Luo, Zhiwei Xiong, Wenjun Zeng

摘要:

时频域掩蔽是单通道语音增强的主流方法。近年来,除了幅度预测之外,相位预测也受到关注。在本文中,我们提出了一个相位和谐波感知的深度神经网络(DNN),名为PHASEN,用于此任务。与以前直接使用复理想比率掩码来监督DNN学习的方法不同,我们设计了一个双流网络,其中幅度流和相位流专用于幅度和相位预测。我们发现,这两个流应该相互沟通,这是至关重要的相位预测。此外,我们提出了频率变换块来捕捉沿频率轴的长程相关性。可视化显示,学习的变换矩阵自发地捕获谐波相关性,这已被证明有助于T-F谱图重建。通过这两项创新,PHASEN获得了处理详细相位模式和利用谐波模式的能力,在AVSpeech + AudioSet数据集上获得了1.76dB的SDR改进。它还在此数据集上实现了Google网络的显着收益。在Voice Bank + DEMAND数据集上,PHASEN在四个指标上都大大优于以前的方法。

英文摘要:

Time-frequency (T-F) domain masking is a mainstream approach for single-channel speech enhancement. Recently, focuses have been put to phase prediction in addition to amplitude prediction. In this paper, we propose a phase-and-harmonics-aware deep neural network (DNN), named PHASEN, for this task. Unlike previous methods that directly use a complex ideal ratio mask to supervise the DNN learning, we design a two-stream network, where amplitude stream and phase stream are dedicated to amplitude and phase prediction. We discover that the two streams should communicate with each other, and this is crucial to phase prediction. In addition, we propose frequency transformation blocks to catch long-range correlations along the frequency axis. The visualization shows that the learned transformation matrix spontaneously captures the harmonic correlation, which has been proven to be helpful for T-F spectrogram reconstruction. With these two innovations, PHASEN acquires the ability to handle detailed phase patterns and to utilize harmonic patterns, getting 1.76dB SDR improvement on AVSpeech + AudioSet dataset. It also achieves significant gains over Google's network on this dataset. On Voice Bank + DEMAND dataset, PHASEN outperforms previous methods by a large margin on four metrics.

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。

↑