Voice conversion towards modeling dynamic characteristics using switching state space model

来源 :Science China(Information Sciences) | 被引量 : 0次 | 上传用户:rona
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
In the literature of voice conversion(VC),the method based on statistical Gaussian mixture model(GMM)serves as a benchmark.However,one of the inherent drawbacks of GMM is well-known as discontinuity problem,which is caused by transforming features on a frame-by-frame basis,thus ignoring the dynamics between adjacent frames and fnally resulting in degraded quality of the converted speech.A variety of algorithms have been proposed to overcome this defciency,among which the state space model(SSM)based method provides some promising results.In this paper,we proceed by presenting an enhanced version of the traditional SSM,namely,the switching SSM(SSSM).This new structure is more flexible than the conventional one in that it allows using mixture of components to account for the rapid transitions between neighboring frames.Moreover,physical meaning of the model parameters of SSSM has been examined in depth,leading to efcient application-specifc training and transforming procedures of VC.Experiments including both objective and subjective measurements were conducted to compare the performances of the conventional and the proposed SSM-based methods,which have convinced that obvious improvements in both aspects of similarity and quality can be obtained by SSSM. In the literature of voice conversion (VC), the method based on statistical Gaussian mixture model (GMM) serves as a benchmark. Yet, one of the underlying drawbacks of GMM is well-known as discontinuity problem, which is caused by transforming features on a frame-by-frame basis, thus ignoring the dynamics between adjacent frames and fnally resulting in degraded quality of the converted speech. A variety of algorithms have been proposed to overcome this defciency, among which the state space model (SSM) based method provides some of the results.In this paper, we proceed by presenting an enhanced version of the traditional SSM, namely, the switching SSM (SSSM) .This new structure is more flexible than the conventional one in that it allows using mixture of components to account for the rapid transitions between neighboring frames. Moreover, physical meaning of the model parameters of SSSM has been examined in depth, leading to efcient application-specifc training and transforming procedures of VC.Exper iments including both objective and subjective measurements were conducted to compare the performances of the conventional and the proposed SSM-based methods, which have convinced that obvious improvements in both aspects of similarity and quality can be obtained by SSSM.
其他文献
目的 了解四川省西昌市2008-2018年初始抗病毒治疗HIV感染者死亡和脱失的情况及其影响因素.方法 采用回顾性队列研究的方法,从艾滋病基本防治信息系统选取2008-2018年在西昌
目的 通过检测不同型别输入性登革热患者血中细胞因子及肝功能的水平,探讨细胞因子与肝功能的相关性.方法 对2012-2018年昆明市第三人民医院收治的登革热病例进行回顾性分析.
目的 了解景洪市南鳢感染吸虫囊蚴情况,为制定当地鱼源性吸虫病的防治策略提供依据.方法 选取景洪市主要的两种海拔和气候代表类型勐养镇和普文镇为调查点,分别从当地农贸市
目的 评价GeneXpert MTB/RIF(Xpert)技术在肺结核病实验室诊断中的应用价值.方法 收集2018年1月-12月苏州市第五人民医院收治的疑似肺结核患者标本566份,其中痰标本421份,纤
目的 分析辽宁省近年来登革热疫情特点及流行规律,为制定预防控制措施提供依据.方法 收集国家疾病监测信息报告管理系统2014-2018年登革热基本信息,个案流行病学调查资料,用
2008年4月7日12时,辽中县疾病预防控制中心接到养士堡乡电话报告,养士堡乡四和村李某突然发热,体温达39.5℃,并伴有咳嗽、咽痛、鼻塞、头痛和全身不适等症状;患者家里同时有
目的 分析拉米夫定联合醋酸泼尼松及免疫抑制剂治疗活动性乙肝相关性膜性肾病取得的临床疗效.方法 筛选西宁市第二人民医院2016年1月-2018年6月收治的120例活动性乙肝相关性
Hybrid optical switching networks make full use of the advantages of Optical Circuit Switching(OCS)and Optical Burst Switching(OBS).In parallel hybrid optical s
目的 了解中山市流感嗜血杆菌的临床分布并对其耐药性进行分析,为更好地指导临床用药提供依据.方法 选取中山大学附属中山医院2014-2017年从临床标本中分离的406株流感嗜血杆
目的 分析病理性黄疸患儿巨细胞病毒(CMV)感染情况,探讨母乳CMV-DNA检测的临床意义.方法 选取庆阳市人民医院住院的病理性黄疸新生儿300例,用FQ-PCR方法检测患儿血浆、外周血