arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1608.01953cs.SD
收藏

用于音频声源分离的基于模型的STFT相位恢复

Model-based STFT phase recovery for audio source separation

Tampere University of Technology(坦佩雷理工大学);Télécom ParisTech(巴黎高等电信学院);LTCI, Télécom ParisTech, Université Paris-Saclay(巴黎萨克雷大学巴黎高等电信学院LTCI实验室)

Paul Magron, Roland Badeau, Bertrand David

摘要:

对于音频声源分离应用,通常估计每个声源的短时傅立叶变换(STFT)的幅度。为了进一步合成时域信号,需要恢复相应复值STFT的相位。该领域的大多数作者选择Wiener滤波方法,其归结为使用原始混合物的相位。本文则采取了不同的观点。许多音乐事件部分地由缓慢变化的正弦波组成,并且这些频率分量随时间的STFT相位增量采用特定形式。一旦获得短期频率估计,这允许通过展开技术进行相位恢复。在此,提出了一种新的迭代声源分离过程,建立在这些结果。它是通过辅助函数法使混合误差最小化。这个过程是通过利用展开技术,以产生估计,受益于时间连续性属性初始化。对现实音乐作品进行的实验表明,在精确的幅度估计下,该过程优于最先进的一致性维纳滤波器。

英文摘要:

For audio source separation applications, it is common to estimate the magnitude of the short-time Fourier transform (STFT) of each source. In order to further synthesizing time-domain signals, it is necessary to recover the phase of the corresponding complex-valued STFT. Most authors in this field choose a Wiener-like filtering approach which boils down to using the phase of the original mixture. In this paper, a different standpoint is adopted. Many music events are partially composed of slowly varying sinusoids and the STFT phase increment over time of those frequency components takes a specific form. This allows phase recovery by an unwrapping technique once a short-term frequency estimate has been obtained. Herein, a novel iterative source separation procedure is proposed which builds upon these results. It consists in minimizing the mixing error by means of the auxiliary function method. This procedure is initialized by exploiting the unwrapping technique in order to generate estimates that benefit from a temporal continuity property. Experiments conducted on realistic music pieces show that, given accurate magnitude estimates, this procedure outperforms the state-of-the-art consistent Wiener filter.

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。

↑