专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09002706B2 Cut and paste spoofing detection using dynamic time warping 有权
标题翻译：使用动态时间扭曲来剪切和粘贴欺骗检测
公开(公告)号：US09002706B2
公开(公告)日：2015-04-07
申请号：US13515281
申请日：2009-12-10
申请人： Jesus Antonio Villalba Lopez , Alfonso Ortega Gimenez , Eduardo Lleida Solano , Sara Varela Redondo , Marta Garcia Gomar
发明人： Jesus Antonio Villalba Lopez , Alfonso Ortega Gimenez , Eduardo Lleida Solano , Sara Varela Redondo , Marta Garcia Gomar
IPC分类号： G10L15/00 , G10L17/00 , B66B13/26 , G10L17/02 , G10L17/24
CPC分类号： G10L17/00 , B66B13/26 , G10L17/02 , G10L17/06 , G10L17/24 , G10L17/26
摘要： The invention refers to a method for comparing voice utterances, the method comprising the steps: extracting a plurality of features (201) from a first voice utterance of a given text sample and extracting a plurality of features (201) from a second voice utterance of said given text sample, wherein each feature is extracted as a function of time, and wherein each feature of the second voice utterance corresponds to a feature of the first voice utterance; applying dynamic time warping (202) to one or more time dependent characteristics of the first and/or second voice utterance e.g. by minimizing one or more distance measures, wherein a distance measure is a measure for the difference of a time dependent characteristic of the first voice utterance and a corresponding time dependent characteristic of the second voice utterance, and wherein a time dependent characteristic of a voice utterance is a time dependent characteristic of either a single feature or a combination of two or more features; calculating a total distance measure (203), wherein the total distance measure is a measure for the difference between the first voice utterance of the given text sample and the second voice utterance of said given text sample, wherein the total distance measure is calculated based on one or more pairs of said time dependent characteristic, and wherein a pair of time dependent characteristic is calculate total composed of a time dependent characteristic of the first or second voice utterance and of a dynamically time warped (202) time dependent characteristic of the respectively second or first voice utterance, or wherein a pair of time dependent characteristic is composed of a dynamically time warped (202) time dependent characteristic of the first voice utterance and of a dynamically time warped (202) time dependent characteristic of the second voice utterance.
摘要翻译：本发明涉及一种用于比较语音话语的方法，所述方法包括以下步骤：从给定文本样本的第一语音发音中提取多个特征（201），并从第二话音语音提取多个特征（201）所述给定文本样本，其中每个特征被提取为时间的函数，并且其中所述第二语音话语的每个特征对应于所述第一语音话语的特征; 将动态时间扭曲（202）应用于第一和/或第二语音话语的一个或多个时间依赖特性，例如。通过最小化一个或多个距离度量，其中距离度量是用于第一语音发音的时间相关特性与第二语音发音的对应时间相关特性的差的度量，并且其中语音话语的时间相关特性是单个特征或两个或更多个特征的组合的时间依赖特性; 计算总距离测量（203），其中所述总距离测量是用于所述给定文本样本的所述第一语音发音与所述给定文本样本的所述第二语音发声之间的差的度量，其中所述总距离测量基于一对或多对所述时间依赖特性，并且其中一对时间依赖特性是计算由第一或第二语音话语的时间依赖特性组成的总和以及分别第二或第二语音话语的动态时间扭曲（202）时间依赖特性或第一语音话语，或者其中一对时间依赖特性由第一语音话语的动态时间扭曲（202）时间依赖特性和第二语音话语的动态时间扭曲（202）时间依赖特性组成。

2. 发明申请

US20140081638A1 CUT AND PASTE SPOOFING DETECTION USING DYNAMIC TIME WARPING 有权
标题翻译：使用动态时间加热的切割和馅料检测
公开(公告)号：US20140081638A1
公开(公告)日：2014-03-20
申请号：US13515281
申请日：2009-12-10
申请人： Jesus Antonio Villalba Lopez , Alfonso Ortega Gimenez , Eduardo Lleida Solano , Sara Varela Redondo , Marta Garcia Gomar
发明人： Jesus Antonio Villalba Lopez , Alfonso Ortega Gimenez , Eduardo Lleida Solano , Sara Varela Redondo , Marta Garcia Gomar
IPC分类号： G10L17/00
CPC分类号： G10L17/00 , B66B13/26 , G10L17/02 , G10L17/06 , G10L17/24 , G10L17/26
摘要： The invention refers to a method for comparing voice utterances, the method comprising the steps: extracting a plurality of features (201) from a first voice utterance of a given text sample and extracting a plurality of features (201) from a second voice utterance of said given text sample, wherein each feature is extracted as a function of time, and wherein each feature of the second voice utterance corresponds to a feature of the first voice utterance; applying dynamic time warping (202) to one or more time dependent characteristics of the first and/or second voice utterance e.g. by minimizing one or more distance measures, wherein a distance measure is a measure for the difference of a time dependent characteristic of the first voice utterance and a corresponding time dependent characteristic of the second voice utterance, and wherein a time dependent characteristic of a voice utterance is a time dependent characteristic of either a single feature or a combination of two or more features; calculating a total distance measure (203), wherein the total distance measure is a measure for the difference between the first voice utterance of the given text sample and the second voice utterance of said given text sample, wherein the total distance measure is calculated based on one or more pairs of said time dependent characteristic, and wherein a pair of time dependent characteristic is calculate total composed of a time dependent characteristic of the first or second voice utterance and of a dynamically time warped (202) time dependent characteristic of the respectively second or first voice utterance, or wherein a pair of time dependent characteristic is composed of a dynamically time warped (202) time dependent characteristic of the first voice utterance and of a dynamically time warped (202) time dependent characteristic of the second voice utterance.
摘要翻译：本发明涉及一种用于比较语音话语的方法，所述方法包括以下步骤：从给定文本样本的第一语音发音中提取多个特征（201），并从第二话音语音提取多个特征（201）所述给定文本样本，其中每个特征被提取为时间的函数，并且其中所述第二语音话语的每个特征对应于所述第一语音话语的特征; 将动态时间扭曲（202）应用于第一和/或第二语音话语的一个或多个时间依赖特性，例如。通过最小化一个或多个距离度量，其中距离度量是用于第一语音发音的时间相关特性与第二语音发音的对应时间相关特性的差的度量，并且其中语音话语的时间相关特性是单个特征或两个或更多个特征的组合的时间依赖特性; 计算总距离测量（203），其中所述总距离测量是用于所述给定文本样本的所述第一语音发音与所述给定文本样本的所述第二语音发声之间的差的度量，其中所述总距离测量基于一对或多对所述时间依赖特性，并且其中一对时间依赖特性是计算由第一或第二语音话语的时间依赖特性组成的总和以及分别第二或第二语音话语的动态时间扭曲（202）时间依赖特性或第一语音话语，或者其中一对时间依赖特性由第一语音话语的动态时间扭曲（202）时间依赖特性和第二语音话语的动态时间扭曲（202）时间依赖特性组成。

3. 发明申请

US20050058278A1 Method and System for Suppressing Echoes and Noises in Environments Under Variable Acoustic and Highly Fedback Conditions 失效
标题翻译：用于抑制可变声学和高度反馈条件下环境中回波和噪声的方法和系统
公开(公告)号：US20050058278A1
公开(公告)日：2005-03-17
申请号：US10707403
申请日：2003-12-11
申请人： Fernando Gallego Hugas , Eduardo Lleida Solano , Enrique Masgrau Gomez , Alfonso Ortega Gimenez
发明人： Fernando Gallego Hugas , Eduardo Lleida Solano , Enrique Masgrau Gomez , Alfonso Ortega Gimenez
IPC分类号： G10L21/0208 , H04M9/08 , H04R3/02
CPC分类号： G10L21/0208 , G10L2021/02082 , H04M9/082 , H04R3/02
摘要： Method and system for canceling echoes and noises in environments with variable acoustic conditions and high feedback, such as the interior of an automotive vehicle, permitting audible communication between the occupants, comprising one/several microphone/s (1) for a speech signal (5) and A/D, D/A converters, amplification and filtering means generating an electric signal (13) reproduced as an acoustic signal (7) by a speaker (3), and an echo canceller (15) using said signal (13) and an electric signal (10) from the microphone integrating the feedback of said signal (7), another speech signal (5) and noise (9) seized by the microphone (1), the system (15) being applied to eliminating said feedback, the proposed method and system providing an additional filtering of an electric output signal (11) of the canceling device (15), after treatment of said signal, comprising a time variant filter that suppresses the residual acoustic echo not cancelled by the system (15) and the noise seized by said microphone/s (1).
摘要翻译：用于消除具有可变声学条件和高反馈的环境中的回波和噪声的方法和系统，例如机动车辆的内部，允许乘员之间的可听见的通信，包括用于语音信号的一个/多个麦克风（1））和A / D，D / A转换器，放大和滤波装置，用于产生由扬声器（3）作为声音信号（7）再现的电信号（13），以及使用所述信号（13）的回波消除器（15）以及来自所述麦克风的电信号（10），其积分所述信号（7）的反馈，由所述麦克风（1）占据的另一语音信号（5）和噪声（9），所述系统（15）被应用于消除所述反馈所提出的方法和系统在处理所述信号之后对消除装置（15）的电输出信号（11）进行附加滤波，包括抑制未被系统取消的残余声学回声的时变滤波器（15））和缉获的噪音b y说麦克风/ s（1）。

4. 发明授权

US07068798B2 Method and system for suppressing echoes and noises in environments under variable acoustic and highly feedback conditions 失效
标题翻译：用于在不同声学和高反馈条件下的环境中抑制回波和噪声的方法和系统
公开(公告)号：US07068798B2
公开(公告)日：2006-06-27
申请号：US10707403
申请日：2003-12-11
申请人： Fernando Gallego Hugas , Eduardo Lleida Solano , Enrique Masgrau Gomez , Alfonso Ortega Gimenez
发明人： Fernando Gallego Hugas , Eduardo Lleida Solano , Enrique Masgrau Gomez , Alfonso Ortega Gimenez
IPC分类号： H04B15/00
CPC分类号： G10L21/0208 , G10L2021/02082 , H04M9/082 , H04R3/02
摘要： Method and system for canceling echoes and noises in environments with variable acoustic conditions and high feedback, such as the interior of an automotive vehicle, permitting audible communication between the occupants, comprising one/several microphone/s (1) for a speech signal (5) and A/D, D/A converters, amplification and filtering means generating an electric signal (13) reproduced as an acoustic signal (7) by a speaker (3), and an echo canceller (15) using said signal (13) and an electric signal (10) from the microphone integrating the feedback of said signal (7), another speech signal (5) and noise (9) seized by the microphone (1), the system (15) being applied to eliminating said feedback, the proposed method and system providing an additional filtering of an electric output signal (11) of the canceling device (15), after treatment of said signal, comprising a time variant filter that suppresses the residual acoustic echo not cancelled by the system (15) and the noise seized by said microphone/s (1).
摘要翻译：用于消除具有可变声学条件和高反馈的环境中的回波和噪声的方法和系统，例如机动车辆的内部，允许乘员之间的可听见的通信，包括用于语音信号的一个/多个麦克风（1））和A / D，D / A转换器，放大和滤波装置，用于产生由扬声器（3）作为声音信号（7）再现的电信号（13），以及使用所述信号（13）的回波消除器（15）以及来自所述麦克风的电信号（10），其积分所述信号（7）的反馈，由所述麦克风（1）占据的另一语音信号（5）和噪声（9），所述系统（15）被应用于消除所述反馈所提出的方法和系统在处理所述信号之后对消除装置（15）的电输出信号（11）提供额外的滤波，包括抑制未被系统消除的残留声学回声的时变滤波器 em（15）和由所述麦克风/ s（1）捕获的噪声。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式