Voice conversion (VC) based on Gaussian mixture model (GMM) is the most classic and common method which converts the source spectrum to target spectrum. However this method is prone to over-fitting because of its frame-by-frame conversion. The VC with non-negative matrix factorization (NMF) is presented in this paper, which can keep spectrum from over-fitting by adjusting the size of basis vector (dictionary). In order to realize the non-linear mapping better, kernel NMF (KNMF) is adopted to achieve spectrum mapping. In addition, to increase the accuracy of conversion, KNMF combined with GMM (GKNMF) is also introduced into VC. In the end, KNMF, GKNMF, GMM, principal component regression (PCR), PCR combined with GMM (GPCR), partial least square regression (PLSR), NMF correlation-based frequency warping (NMF-CFW) and deep neural network (DNN) methods are compared with each other. The proposed GKNMF gets better performance in both objective evaluation and subjective evaluation.
针对传统视觉词袋(Bag Of Visual Words,BOVW)模型缺少空间信息,且不能充分表达图像所属类别共有特征的问题,提出一种基于最大频繁项集的视觉词袋表示方法。该方法在排除孤立特征点的基础上,引入环形区域划分的思想,嵌入更多的空间信息。通过对不同环的视觉单词进行频繁项挖掘得到新的视觉单词表示,能有效提高同类别图像视觉单词的相似程度,而使不同类别视觉单词的差异更为显著。通过在图像数据集COREL及Caltech-256上进行分类实验,验证了该方法的有效性和可行性。
目的评估不同致痛性操作对新生儿疼痛评分和生理指标的影响。方法2009年3月1日至5月31日入住南京医科大学附属南京儿童医院新生儿医疗中心的新生儿108例,其中早产儿46例,足月儿62例。通过实时床边观察和数码录像收集新生儿从入院到出院期间所有诊疗需要所致的疼痛性操作过程,应用新生儿面部编码系统(Neonatal Facial Coding System,NFCS)、新生儿疼痛评估量表(Neonatal In fant Pain Scale,NIPS)及早产儿疼痛量表(PrematureInfantPainProfile,PIPP)评估新生儿的疼痛反应,同时记录操作前后患儿心率和血氧饱和度变化。采用Student—t检验、7。检验和重复测量方差分析比较不同致痛性操作对新生儿疼痛评分和生理指标的影响。结果早产儿共接受不同类型致痛性操作6966例次,经历最多的前3种致痛性操作分别为气管内吸引(23.6%,1645/6966)、口鼻腔吸引(18.3%,1278/6966)和外周静脉穿刺置管(17.2%,1195/6966),而足月儿经历最多的前3种致痛性操作分别为外周静脉穿刺置管(27.0%,989/3667)、拔除留置针(20.5%,751/3667)和去除胶布(18.4%,675/3667)。早产儿致痛性操作疼痛评分较高的前3种分别是气管插管ENFCS(7.00±1.66)分,PIPP(14.08±3.54)分]、股静脉穿刺ENFCS(6.52±1.66)分,PIPP(12.15±3.11)分]和腋静脉穿刺ENFCS(5.75±1.89)分,PIPP(11.75±4.19)分];足月儿致痛性操作疼痛评分较高的前3种分别是股静脉穿刺ENFCS(6.68±1.34)分,NIPS(5.58土1.32)分]、去除胶布[NFCS(6.00±1.41)分,NIPS(5.67±0.58)分]及腹壁静脉穿刺ENFCS(6.00±0.00)分,NIPS(5.50±0.71)分]。不同类型的致痛性操作引起的足月儿心率(F=0.186,P=0.836)及血氧饱和度(F=1.672,P=0.198)变化差异无统计学意义。结论住院新生儿