利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

11 条记录 (耗时 0.025 秒)

    Test signalling
    1.
    发明授权
    Test signalling 有权
    测试信号

    公开(公告)号：US07978613B2

    公开(公告)日：2011-07-12

    申请号：US10275475

    申请日：2001-05-10

    申请人： Philip Gray ,  Michael P Hollier ,  Richard JB Reynolds ,  Antony W Rix

    发明人： Philip Gray ,  Michael P Hollier ,  Richard JB Reynolds ,  Antony W Rix

    IPC分类号： H04J3/14 ,  H04M3/26 ,  H04B17/00 ,  G10L15/20 ,  G01R31/00

    CPC分类号： H04W24/00 ,  H04B17/309 ,  H04M3/2236

    摘要： The degree of degradation imposed on signals transmitted over a communications link from a transmitter to a receiver is tested. A predetermined test signal is transmitted using spare capacity detected by a voice activity detector when no speech is to be transmitted over the communications link. The test signal received by the receiver is compared with the reference signal, and a measure of the degradation of signals caused by the communications link is generated therefrom.

    摘要翻译： 测试通过从发射机到接收机的通信链路传输的信号的劣化程度。 当通过通信链路不发送语音时，使用由语音活动检测器检测到的备用容量来发送预定的测试信号。 将由接收机接收的测试信号与参考信号进行比较，并从其产生由通信链路引起的信号劣化的量度。

    Test signalling
    2.
    发明授权
    Test signalling 有权
    测试信号

    公开(公告)号：US07050924B2

    公开(公告)日：2006-05-23

    申请号：US10276711

    申请日：2001-05-25

    申请人： Antony W Rix ,  Philip Gray ,  Richard J B Reynolds ,  Michael P Hollier

    发明人： Antony W Rix ,  Philip Gray ,  Richard J B Reynolds ,  Michael P Hollier

    IPC分类号： H04B17/00

    CPC分类号： H04W24/00 ,  H04M3/22

    摘要： The perceptibility of degradations caused to signals transmitted over a transmission medium is measured by generating one or more predetermined transmission degradation conditions (et) and subjecting a test signal (St) to the transmission degradation conditions (et) in a network simulation device. The degree M(e) to which the or each transmission degradation condition (et) is perceptible to the human perceptual system is measured and a data set is generated and stored for converting one or more transmission degradation conditions (et) to respective values of perceptibility M(e). The data set may be a look-up table or an empirically determined formula. The data set may then be used on live traffic (S′), by identifying objectively measured transmission degradation conditions (e) in the received signal (S′) and retrieving from the data set in the data storage means (7) a value of perceptibility (M) associated with the transmission degradation conditions (e) so identified. In this way a measure of the subjective significance of degradation in the signal (S′) can be derived from objective measures of degradation.

    摘要翻译： 通过产生一个或多个预定的传输劣化条件（e> t）并对测试信号（S SUB）进行测量，来测量对通过传输介质传输的信号造成的劣化的可感知性， 到网络仿真设备中的传输劣化条件（e> t）。 测量对人感知系统感知到或每个传输劣化条件（e t）的程度M（e），并且生成并存储用于转换一个或多个传输劣化条件的数据集 （e /）相应的感知度值M（e）。 数据集可以是查找表或经验确定的公式。 然后可以通过在接收到的信号（S'）中识别客观测量的传输劣化条件（e）并且从数据存储装置（7）中的数据集中检索数据集，从而可以在实时业务（S'）上使用数据集 与所识别的传输降解条件（e）相关的感知度（M）。 以这种方式，信号（S'）退化的主观意义的度量可以从客观的降解测量得出。

    Speech-quality assessment method and apparatus that identifies part of a signal not generated by human tract
    5.
    发明授权
    Speech-quality assessment method and apparatus that identifies part of a signal not generated by human tract 有权
    语音质量评估方法和设备，其识别不是由人类产生的信号的一部分

    公开(公告)号：US08682650B2

    公开(公告)日：2014-03-25

    申请号：US11321045

    申请日：2005-12-30

    申请人： Philip Gray ,  Michael P Hollier

    发明人： Philip Gray ,  Michael P Hollier

    IPC分类号： G10L25/00 ,  G10L25/30 ,  G10L25/75

    CPC分类号： G10L25/69

    摘要： Non-intrusive speech-quality assessment uses vocal-tract models, in particular for testing telecommunications systems and equipment. This process requires reduction of the speech stream under assessment into a set of parameters that are sensitive to the types of distortion to be assessed. Once parameterized, the data is used to generate a set of physiologically-based rules for error identification, using a parametric modeling of the shape of the vocal tract itself, by comparison between derived parameters and the output of models of physiologically realistic forms for the vocal tract, and the application of physical constraints on how these can change over time.

    摘要翻译： 非侵入式语音质量评估使用声道模型，特别是用于测试电信系统和设备。 该过程需要将评估中的语音流减少为对待评估的失真类型敏感的一组参数。 一旦参数化，数据就被用于生成一组基于生理学的错误识别规则，使用对声道本身形状的参数化建模，通过派生参数与生理现实形式的声音模型的输出之间的比较 以及对这些随时间变化的物理限制的应用。

    Training process for the classification of a perceptual signal
    6.
    发明授权
    Training process for the classification of a perceptual signal 失效
    感知信号分类的训练过程

    公开(公告)号：US6119083A

    公开(公告)日：2000-09-12

    申请号：US43410

    申请日：1998-03-19

    申请人： Michael P Hollier ,  Philip Gray

    发明人： Michael P Hollier ,  Philip Gray

    IPC分类号： G10L19/018 ,  G10L25/30 ,  G10L25/69 ,  H04M3/22 ,  G01L15/06

    CPC分类号： G10L25/69 ,  G10L19/018 ,  H04M3/22 ,  H04M3/2236 ,  G10L25/30 ,  H04M2201/40

    摘要： Training apparatus and method for establishing the network definition function of a trainable processing apparatus for analyzing a signal, includes providing a training sequence having a first signal and a distorted version of the first signal, receiving the training sequence and generating a distortion perception measure for indicating the extent to which the distortion would be perceptible to a human observer, and applying the distortion perception measure to the trainable processing apparatus to determine the network definition function.

    摘要翻译： PCT No.PCT / GB97 / 00265 Sec。 371日期：1998年3月19日 102（e）1998年3月19日PCT 1997年1月30日PCT PCT。 出版物WO97 / 32428 日期1997年9月4日用于建立用于分析信号的可训练处理装置的网络定义功能的训练装置和方法包括提供具有第一信号和第一信号的失真版本的训练序列，接收训练序列并产生 用于指示失真对人类观察者可感知的程度的失真感知测量，以及将可变性感知测量应用于可训练处理设备以确定网络定义功能。

    Training process
    8.
    发明授权
    Training process 失效
    培训过程

    公开(公告)号：US5799133A

    公开(公告)日：1998-08-25

    申请号：US671931

    申请日：1996-06-27

    申请人： Michael P. Hollier ,  Philip Gray

    发明人： Michael P. Hollier ,  Philip Gray

    IPC分类号： G10L19/018 ,  G10L25/30 ,  G10L25/69 ,  H04B1/66 ,  H04M3/22 ,  G06F17/00

    CPC分类号： G10L25/69 ,  G10L19/018 ,  H04B1/665 ,  H04M3/22 ,  H04M3/2236 ,  G10L25/30 ,  H04M2201/40

    摘要： A training apparatus for establishing the network definition function of a trainable processing apparatus, such as, for example, a neural network, is disclosed. The training apparatus analyzes a signal and includes means for providing a training sequence, the training sequence including a first signal and a distorted version of the first signal. The training sequence is transmitted to an analysis means which generates a distortion perception measure that indicates the extent to which the distortion would be perceptible to a human observer. The network definition function is determined by applying the distortion perception measure to the trainable processing apparatus.

    摘要翻译： 公开了一种用于建立可训练处理装置（例如神经网络）的网络定义功能的训练装置。 训练装置分析信号并包括用于提供训练序列的装置，训练序列包括第一信号和第一信号的失真版本。 将训练序列发送到分析装置，该分析装置产生失真感知度量，该失真感知度量指示失真对人类观察者可感知的程度。 网络定义功能是通过对可训练处理设备应用失真感知测量来确定的。

    Non-intrusive speech-quality assessment
    9.
    发明申请
    Non-intrusive speech-quality assessment 有权
    非侵入性语音质量评估

    公开(公告)号：US20060224387A1

    公开(公告)日：2006-10-05

    申请号：US11321045

    申请日：2005-12-30

    申请人： Philip Gray ,  Michael Hollier

    发明人： Philip Gray ,  Michael Hollier

    IPC分类号： G10L13/00

    CPC分类号： G10L25/69

    摘要： Non-intrusive speech-quality assessment uses vocal-tract models, in particular for testing telecommunications systems and equipment. This process requires reduction of the speech stream under assessment into a set of parameters that are sensitive to the types of distortion to be assessed. Once parameterized, the data is used to generate a set of physiologically-based rules for error identification, using a parametric modeling of the shape of the vocal tract itself, by comparison between derived parameters and the output of models of physiologically realistic forms for the vocal tract, and the application of physical constraints on how these can change over time.

    摘要翻译： 非侵入式语音质量评估使用声道模型，特别是用于测试电信系统和设备。 该过程需要将评估中的语音流减少为对待评估的失真类型敏感的一组参数。 一旦参数化，数据就被用于生成一组基于生理学的错误识别规则，使用对声道本身形状的参数化建模，通过派生参数与生理现实形式的声音模型的输出之间的比较 以及对这些随时间变化的物理限制的应用。

    Quality assessment tool
    10.
    发明授权
    Quality assessment tool 有权
    质量评估工具

    公开(公告)号：US07606704B2

    公开(公告)日：2009-10-20

    申请号：US10757365

    申请日：2004-01-14

    申请人： Philip Gray ,  Ludovic Malfait

    发明人： Philip Gray ,  Ludovic Malfait

    IPC分类号： G10L21/00 ,  G10L21/02

    CPC分类号： G10L25/69

    摘要： A non-intrusive speech quality assessment system. A method and apparatus for training a quality assessment tool in which a database comprising a plurality of samples, each with an associated mean opinion score, is divided into a plurality of distortion sets of samples according to a distortion criterion; and a distortion specific assessment handler for each distortion set is trained, such that a fit between a distortion specific quality measure generated from a distortion specific plurality of parameters for a sample and the mean opinion score associated with said sample is optimised. A method and apparatus for assessing speech quality in a telecommunications network in which a dominant distortion type is determined for a sample; a distortion specific plurality of parameters are combined to provide a distortion specific quality measure for each sample; and a quality measure is generated in dependence upon the distortion specific quality measure.

    摘要翻译： 非侵入性语音质量评估系统。 一种用于训练质量评估工具的方法和装置，其中包括具有相关平均意见得分的多个样本的数据库根据失真标准被划分为多个样本的失真集合; 并且对每个失真集合的失真特定评估处理程序进行训练，使得针对样本的失真特定多个参数产生的失真特定质量度量与与所述样本相关联的平均意见得分进行优化。 一种在电信网络中评估语音质量的方法和装置，其中为样本确定显性失真类型; 组合失真特定的多个参数以为每个样本提供失真特定质量测量; 并且根据失真特定质量测量产生质量测量。