检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:刘贻杰 李江春[2] 陈维娜[1] 黄颀涵 LIU Yijie;LI Jiangchun;CHEN Weina;HUANG Qihan(School of Investigation,People's Public Security University of China,Beijing 100038,China;Hubei Key Laboratory of the Forensic Science(Hubei University of Police),Wuhan 430034,China)
机构地区:[1]中国人民公安大学侦查学院,北京100038 [2]法庭科学湖北省重点实验室(湖北警官学院),湖北武汉430034
出 处:《中国人民公安大学学报(自然科学版)》2022年第1期14-20,共7页Journal of People’s Public Security University of China(Science and Technology)
基 金:现场物证溯源技术国家工程实验室开放课题(2019NELKFKT05);法庭科学湖北省重点实验室(湖北警官学院)资助课题(KFKT2021003)。
摘 要:就音段选取长度对基频分析的影响进行实验研究,旨在尝试为语音同一认定中的基频分析提供更可靠的指标。实验从单音节字、多音节词、句子、语段4个音段长度对20位志愿者的录音进行了基频分析,使用方差均值比分析个体稳定性,使用皮尔逊相关性检验初步分析人间差异性,并使用欧氏距离进一步对句子、语段的基频进行综合分析。结果发现,单音节字、多音节词的个人稳定性和人间差异性较差,不适用于基频分析,而句子、语段的基频均值稳定性较强,且综合使用均值、最小值和最大值时发音个体间的差异相对更明显。研究结果表明,截取句子、语段等长时音段进行综合的基频分析,更适用于语音同一认定。The research on the influence of the intercepted length of the speech segment on the fundamental frequency(F0)analysis is to try to provide a more reliable indicator for the F0 analysis in forensic speaker identification.The experiment carried out F0 analysis on the recordings of 20 people from the lengths of four kinds of intercepted segments of monosyllable words,polysyllable words,sentences,and complete segments.The variance mean ratio was used to analyze the stability of individuals,the Pearson correlation test was used to analyze the inter-individual differences,and Euclidean distance was used to further comprehensively analyze the F0 of sentences and complete segments.It could be seen that the individual stability and inter-individual differences of monosyllable words and polysyllable words are poor,and they are not suitable for identification.However,the F0 of sentences and complete segments are relatively stable,and the difference between individuals is relatively more obvious when the mean,minimum values and maximum value are combined.Results show that intercepting sentences and other long segments for comprehensive F0 analysis is more suitable for forensic speaker identification.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:18.217.108.153