| 侯代文,殷福亮,陈喆.基于分层采样粒子滤波的说话人跟踪方法[J].,2009,(4):580-586 |
| 基于分层采样粒子滤波的说话人跟踪方法 |
| Speaker tracking method using layered sampling particle filter |
| |
| DOI：10.7511/dllgxb200904020 |
| 中文关键词: 说话人跟踪 粒子滤波 波达方向估计 时间延迟估计 分层采样 |
| 英文关键词: speaker tracking particle filter DOA estimation TDOA estimation layered sampling |
| 基金项目:国家自然科学基金资助项目(6077216160372082)；高等学校博士学科点专项科研基金资助项目(200801410015). |
|
| 摘要点击次数: 1249 |
| 全文下载次数: 822 |
| 中文摘要: |
| 利用分层采样方法，融合波达方向和时间延迟两种信息，实现了对说话人的定位与跟踪．分层采样方法考虑波达方向和时间延迟这两种不同观测信息对说话人位置估计精度的差异，将基于波达方向滤波得到的状态后验概率密度函数作为基于时间延迟滤波的重要性采样函数，增强了重要性概率密度函数与后验概率密度函数的相似程度，从而改善了重要性概率密度函数的质量，减小了采样粒子权值的方差，提高了对说话人位置的估计精度．仿真实验验证了该方法的有效性． |
| 英文摘要: |
| Utilizing layered sampling method, both direction of arrival (DOA) and time difference of arrival (TDOA) of speech source are fused to localize and track the speaker. Since the measurement modalities differ in the level of information which they provide about the state, the layered sampling method constructs an informed proposal by integrating filtering results from DOA measurement, then particles are sampled from this proposal in TDOA measurement based particle filter. As the similarity between the importance density function and the posterior density function is enhanced, the quality of the proposal function is improved and variance of sample weights is decreased, thus the speaker localization accuracy is improved. Simulation results of two scenarios show the validity of the proposed method. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |