水声语音通信在海洋工程、海洋科考、水下搜救等领域具有广泛应用。与单边带通信、数字编码调制通信相比,调频水声语音通信具有实现简单方便、抗幅度衰落性能好的特点,但浅海水声信道具有的复杂多径效应及噪声严重影响其获得的语音音质...水声语音通信在海洋工程、海洋科考、水下搜救等领域具有广泛应用。与单边带通信、数字编码调制通信相比,调频水声语音通信具有实现简单方便、抗幅度衰落性能好的特点,但浅海水声信道具有的复杂多径效应及噪声严重影响其获得的语音音质,容易出现语音含混、语义难辨等问题。本文通过浅海不同距离、不同多径信道下的海试实验比较了采用非线性解调法和正交解调法的调频语音通信性能,并通过客观语音质量评估PESQ(Perceptual evaluation of speech quality)方法对调频水声语音通信音质进行量化评估。展开更多
给出一种有效的噪声压缩算法,提供了高分辨率的掩蔽感知模型,并对K a lm an滤波模型进行了改进。算法通过计算噪声掩蔽参数,可以适时更新数据参数,压缩信号噪声。实验表明,本文算法没有延迟,语音质量感知评估(Perceptua l eva luation o...给出一种有效的噪声压缩算法,提供了高分辨率的掩蔽感知模型,并对K a lm an滤波模型进行了改进。算法通过计算噪声掩蔽参数,可以适时更新数据参数,压缩信号噪声。实验表明,本文算法没有延迟,语音质量感知评估(Perceptua l eva luation of speech qua lity scores,PESQ)值高,对窄带及宽带信号噪声的压缩均有满意效果。展开更多
VoIP的服务质量(QoS,Quality of Service)评估可以采用一系列可度量的参数来描述:业务可用性、吞吐量、延迟、抖动、分组丢失率等。现有的感知语音质量评价(PESQ)很难对不同环境下的网络结构进行实时和恰当的语音等级质量分类。为了能...VoIP的服务质量(QoS,Quality of Service)评估可以采用一系列可度量的参数来描述:业务可用性、吞吐量、延迟、抖动、分组丢失率等。现有的感知语音质量评价(PESQ)很难对不同环境下的网络结构进行实时和恰当的语音等级质量分类。为了能够综合考虑几种QoS相关因素,在给出改进的自组织映射神经网络模型(ESOMNN)的基础上,利用ESOM能够对高维输入数据有效分类的特点,提出了将端到端延迟、丢包率、抖动、语音编码以及测试系统标识作为ESOMNN的输入数据,在对采样数据进行训练后可自动完成语音质量评价和映射,并能根据得到的实时变量有效地评价包含多种相关因素的QoS级别。展开更多
Objective speech quality is difficult to be measured without the input reference speech.Mapping methods using data mining are investigated and designed to improve the output-based speech quality assessment algorithm.T...Objective speech quality is difficult to be measured without the input reference speech.Mapping methods using data mining are investigated and designed to improve the output-based speech quality assessment algorithm.The degraded speech is firstly separated into three classes(unvoiced,voiced and silence),and then the consistency measurement between the degraded speech signal and the pre-trained reference model for each class is calculated and mapped to an objective speech quality score using data mining.Fuzzy Gaussian mixture model(GMM)is used to generate the artificial reference model trained on perceptual linear predictive(PLP)features.The mean opinion score(MOS)mapping methods including multivariate non-linear regression(MNLR),fuzzy neural network(FNN)and support vector regression(SVR)are designed and compared with the standard ITU-T P.563 method.Experimental results show that the assessment methods with data mining perform better than ITU-T P.563.Moreover,FNN and SVR are more efficient than MNLR,and FNN performs best with 14.50% increase in the correlation coefficient and 32.76% decrease in the root-mean-square MOS error.展开更多
文摘水声语音通信在海洋工程、海洋科考、水下搜救等领域具有广泛应用。与单边带通信、数字编码调制通信相比,调频水声语音通信具有实现简单方便、抗幅度衰落性能好的特点,但浅海水声信道具有的复杂多径效应及噪声严重影响其获得的语音音质,容易出现语音含混、语义难辨等问题。本文通过浅海不同距离、不同多径信道下的海试实验比较了采用非线性解调法和正交解调法的调频语音通信性能,并通过客观语音质量评估PESQ(Perceptual evaluation of speech quality)方法对调频水声语音通信音质进行量化评估。
文摘给出一种有效的噪声压缩算法,提供了高分辨率的掩蔽感知模型,并对K a lm an滤波模型进行了改进。算法通过计算噪声掩蔽参数,可以适时更新数据参数,压缩信号噪声。实验表明,本文算法没有延迟,语音质量感知评估(Perceptua l eva luation of speech qua lity scores,PESQ)值高,对窄带及宽带信号噪声的压缩均有满意效果。
基金国家自然科学基金(the National Natural Science Foundation of China under Grant No.50427401)。
文摘VoIP的服务质量(QoS,Quality of Service)评估可以采用一系列可度量的参数来描述:业务可用性、吞吐量、延迟、抖动、分组丢失率等。现有的感知语音质量评价(PESQ)很难对不同环境下的网络结构进行实时和恰当的语音等级质量分类。为了能够综合考虑几种QoS相关因素,在给出改进的自组织映射神经网络模型(ESOMNN)的基础上,利用ESOM能够对高维输入数据有效分类的特点,提出了将端到端延迟、丢包率、抖动、语音编码以及测试系统标识作为ESOMNN的输入数据,在对采样数据进行训练后可自动完成语音质量评价和映射,并能根据得到的实时变量有效地评价包含多种相关因素的QoS级别。
基金Projects(61001188,1161140319)supported by the National Natural Science Foundation of ChinaProject(2012ZX03001034)supported by the National Science and Technology Major ProjectProject(YETP1202)supported by Beijing Higher Education Young Elite Teacher Project,China
文摘Objective speech quality is difficult to be measured without the input reference speech.Mapping methods using data mining are investigated and designed to improve the output-based speech quality assessment algorithm.The degraded speech is firstly separated into three classes(unvoiced,voiced and silence),and then the consistency measurement between the degraded speech signal and the pre-trained reference model for each class is calculated and mapped to an objective speech quality score using data mining.Fuzzy Gaussian mixture model(GMM)is used to generate the artificial reference model trained on perceptual linear predictive(PLP)features.The mean opinion score(MOS)mapping methods including multivariate non-linear regression(MNLR),fuzzy neural network(FNN)and support vector regression(SVR)are designed and compared with the standard ITU-T P.563 method.Experimental results show that the assessment methods with data mining perform better than ITU-T P.563.Moreover,FNN and SVR are more efficient than MNLR,and FNN performs best with 14.50% increase in the correlation coefficient and 32.76% decrease in the root-mean-square MOS error.
