Effective Sound Source Separation Using Single Voice Activity Segments for Binaural Sound
Effective Sound Source Separation Using Single Voice Activity Segments for Binaural Sound
复制标题
DOI：
10.23919/apsipa.2018.8659613
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Wataru Noguchi;A. Kawamura;Y. Iiguni
中科院分区：
文献类型：
--
作者：
Wataru Noguchi;A. Kawamura;Y. Iiguni
双耳声音众所周知是一种三维声音，它实现了声音的虚拟现实或声音的增强现实。双耳声音的特征是ILD（耳间声级差）和IPD（耳间相位差）。在本文中，我们提出了一种从观察到的混合信号中分离声源的方法，而不丢失各自的 ILD 和 IPD。所提出的方法是通过改进基于单个语音活动检测的传统声源分离方法而建立的，该方法检测仅包括单个声源的片段。所提出的方法从单个语音活动片段估计 ILD 和 IPD。使用传统方法分离声源后，我们给出了分离声源的估计 ILD 和 IPD，以细化双耳特性。双耳声音的 ILD 和 IPD 估计结果阐明了该方法的有效性。
Binaural sound is well known as a three dimensional sound which achieves a virtual reality of sound, or an augmented reality of sound. Binaural sound is characterized by ILD (Interaural Level Difference) and IPD (Interaural Phase Difference). In this paper, we propose a method to separate sound sources from an observed mixture signal, without losing respective ILD and IPD. The proposed method is established by improving a conventional sound source separation method based on single voice activity detection which detects segments including only single sound source. The proposed method estimates ILD and IPD from the single voice activity segments. After separating the sound sources by using the conventional method, we give the estimated ILD and IPD on the separated sound sources to refine the binaural characteristics. The effectiveness of the proposed method is clarified from estimation results of ILD and IPD for binaural sounds.