| 波达方向初始化空间混合概率模型的语音增强 |
| |
| 引用本文： | 石倩,陈航艇,张鹏远.波达方向初始化空间混合概率模型的语音增强[J].声学学报,2022,47(1):139-150. |
| |
| 作者姓名： | 石倩 陈航艇 张鹏远 |
| |
| 作者单位： | 1. 南京大学声学研究所 物理学院 南京 210093; |
| |
| 基金项目： | 中国科学院战略性先导科技专项项目(XDC08010300);国家自然科学基金项目(11774380,62071461)资助。 |
| |
| 摘 要： | 提出了波达方向初始化空间混合概率模型的语音增强算法.通过声源定位估计出声源波达方向,再根据此计算相对传递函数,进而构造空间协方差矩阵来初始化空间混合概率模型.论证了相对传递函数在作为模型参数中语音协方差矩阵的主特征向量时,空间混合概率模型对应的概率分布可达到最大值,进而使期望最大化算法在迭代时更易收敛,以得到期望的掩蔽...
|
| 关 键 词： | 语音增强 波达方向 掩蔽估计 空间混合概率模型 |
| 收稿时间： | 2021-01-03 |
Direction-guided speech enhancement method of the spatial mixture model |
| |
| SHI Qian,CHEN Hangting,ZHANG Pengyuan.Direction-guided speech enhancement method of the spatial mixture model[J].Acta Acustica,2022,47(1):139-150. |
| |
| Authors: | SHI Qian CHEN Hangting ZHANG Pengyuan |
| |
| Affiliation: | 1. Institute of Acoustics, School of Physics, Nanjing University, Nanjing 210093;2. Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190;3. University of Chinese Academy of Sciences, Beijing 100049 |
| |
| Abstract: | A speech enhancement method using the Direction of Arrival(DOA) to initialize Expectation-Maximization(EM) algorithm is proposed,which can improve the mask estimation performance based on the spatial mixture probabilistic model.DOA is estimated to construct the relative transfer function,and then initializes the spatial covariance matrix It is demonstrated that the probability distribution of the spatial mixture probability model will reach the maximum value when the relative transfer function serves as the main eigenvector of the speech covariance matrix,which makes the EM algorithm easier to converge to obtain the desired mask value.The experiment is verified with the Word Error Rate(WER) on a simulated two-channel dataset and the two-channel part of the CHiME4 dataset.The result shows that directional information improves the speech enhancement performance,reduces the WER by 3.79%,and improves the SDR by 2.00 dB the most. |
| |
| Keywords: | |
| 本文献已被 维普 等数据库收录！ |
| 点击此处可从《声学学报》浏览原始摘要信息 |
|
点击此处可从《声学学报》下载全文 |
|
