Multichannel Online Blind Speech Dereverberation with Marginalization of Static Observation Parameters in a Rao-Blackwellized Particle Filter
Multichannel Online Blind Speech Dereverberation with Marginalization of Static Observation Parameters in a Rao-Blackwellized Particle Filter
复制标题
Rao-Blackwellized 粒子滤波器中静态观测参数边缘化的多通道在线盲语音去混响
DOI：
10.1007/s11265-009-0442-4
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
Evers C
中科院分区：
文献类型：
--
作者：
Evers C
室内混响导致音频信号的可懂度降低和音频信号的频谱着色。因此，声学信号的增强对于高质量音频和场景分析应用至关重要。多个传感器可用于利用来自同一事件的多个观测的统计证据来改进增强。虽然传统的波束成形技术受到干扰混响反射与波束路径的影响，但其他去混响方法通常需要至少部分地了解房间脉冲响应，这在实践中是不可用的，或者依赖于信道估计的逆滤波来获得干净的语音估计，从而导致非最小相位声学脉冲响应的困难。本文提出了一种多传感器的盲去混响方法，在该方法中，源信号和声信道都直接从失真的观测值使用其最优估计器估计。剩余的模型参数使用粒子滤波器从假设分布中采样，从而便于实时去混响。这种方法以前被成功地应用于单传感器盲去混响。在本文中，单通道的方法扩展到多个传感器。由于使用多个传感器的性能改进，证明合成和基带语音的例子。
Room reverberation leads to reduced intelligibility of audio signals and spectral coloration of audio signals. Enhancement of acoustic signals is thus crucial for high-quality audio and scene analysis applications. Multiple sensors can be used to exploit statistical evidence from multiple observations of the same event to improve enhancement. Whilst traditional beamforming techniques suffer from interfering reverberant reflections with the beam path, other approaches to dereverberation often require at least partial knowledge of the room impulse response which is not available in practice, or rely on inverse filtering of a channel estimate to obtain a clean speech estimate, resulting in difficulties with non-minimum phase acoustic impulse responses. This paper proposes a multi-sensor approach to blind dereverberation in which both the source signal and acoustic channel are directly estimated from the distorted observations using their optimal estimators. The remaining model parameters are sampled from hypothesis distributions using a particle filter, thus facilitating real-time dereverberation. This approach was previously successfully applied to single-sensor blind dereverberation. In this paper, the single-channel approach is extended to multiple sensors. Performance improvements due to the use of multiple sensors are demonstrated on synthetic and baseband speech examples.
登录
查看更多内容
DOI：
--
发表时间：
2008
期刊：
影响因子：
--
作者：
N. Gaubitch;Xiang Lin;P. Naylor
通讯作者：
P. Naylor
复子带分解及其在大型自适应滤波问题抽取中的应用
影响因子：
5.4
作者：
J. Reilly;Matthew R. Wilbur;M. Seibert;N. Ahmadvand
通讯作者：
N. Ahmadvand
基于谐波结构的单通道语音信号盲去混响
DOI：
--
发表时间：
2003
期刊：
IEEE International Conference on Acoustics, Speech, and Signal Processing
影响因子：
--
作者：
T. Nakatani;M. Miyoshi
通讯作者：
M. Miyoshi
影响因子：
2.4
作者：
NABELEK, AK;LETOWSKI, TR;TUCKER, FM
通讯作者：
TUCKER, FM
子带自适应滤波器的稳态性能限制
影响因子：
5.4
作者：
Stephan Weiss;A. Stenger;R. Stewart;R. Rabenstein
通讯作者：
R. Rabenstein