海冰密集度数据是开展全球海洋监测和应对气候变化研究的重要数据源,为了研制出分辨率更高,误差更小的北极海冰密集度融合资料,本文使用了多源海冰密集度资料,以OSTIA(Operational Sea Surface Temperature and Ice Analysis)数据集为...海冰密集度数据是开展全球海洋监测和应对气候变化研究的重要数据源,为了研制出分辨率更高,误差更小的北极海冰密集度融合资料,本文使用了多源海冰密集度资料,以OSTIA(Operational Sea Surface Temperature and Ice Analysis)数据集为融合背景场,采用以下方案开展融合研究。首先,对现有5种海冰资料进行质量控制;其次,以OSI SAF(Ocean and Sea Ice Satellite Application Facility)资料为基准,采用概率密度匹配法订正各资料的系统误差;然后,利用小波分解将各资料分解为低频信息和高频信息,对低频信息和高频信息分别计算融合权重和卡尔曼滤波处理;最后,利用小波重构将各资料进行融合,生成0.05°分辨率的北极逐日海冰密集度融合资料。通过对比国际上广泛认可的OISST(Optimum Interpolation Sea Surface Temperature)、OSTIA海冰密集度资料,验证结果显示:融合资料与OISST、OSTIA海冰密集度资料在北极的空间分布上高度一致,相关系数均超过0.967。相对于前人的研究,本融合资料与OISST的偏差由–1.170%减少到–0.108%,与OSTIA的偏差由0.276%减少到–0.156%;与OISST和OSTIA的均方根误差分别由9.835%减少为8.010%以及由7.427%减少为5.140%。本融合资料的偏差以及均方根误差都得到了显著的提升,具有较高的质量。展开更多
A novel technique is proposed to improve the performance of voice activity detection(VAD) by using deep belief networks(DBN) with a likelihood ratio(LR). The likelihood ratio is derived from the speech and noise spect...A novel technique is proposed to improve the performance of voice activity detection(VAD) by using deep belief networks(DBN) with a likelihood ratio(LR). The likelihood ratio is derived from the speech and noise spectral components that are assumed to follow the Gaussian probability density function(PDF). The proposed algorithm employs DBN learning in order to classify voice activity by using the input signal to calculate the likelihood ratio. Experiments show that the proposed algorithm yields improved results in various noise environments, compared to the conventional VAD algorithms. Furthermore, the DBN based algorithm decreases the detection probability of error with [0.7, 2.6] compared to the support vector machine based algorithm.展开更多
基金supported by the KERI Primary Research Program through the Korea Research Council for Industrial Science & Technology funded by the Ministry of Science,ICT and Future Planning (No.15-12-N0101-46)
文摘A novel technique is proposed to improve the performance of voice activity detection(VAD) by using deep belief networks(DBN) with a likelihood ratio(LR). The likelihood ratio is derived from the speech and noise spectral components that are assumed to follow the Gaussian probability density function(PDF). The proposed algorithm employs DBN learning in order to classify voice activity by using the input signal to calculate the likelihood ratio. Experiments show that the proposed algorithm yields improved results in various noise environments, compared to the conventional VAD algorithms. Furthermore, the DBN based algorithm decreases the detection probability of error with [0.7, 2.6] compared to the support vector machine based algorithm.
