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. 发明申请

WO2014048855A1 SPEAKER RECOGNITION 审中-公开
标题翻译：扬声器识别
公开(公告)号：WO2014048855A1
公开(公告)日：2014-04-03
申请号：PCT/EP2013/069626
申请日：2013-09-20
申请人： AGNITIO,S.L
发明人： BUERA RODRIGUEZ, Luis , VAQUERO AVILES-CASCO, Carlos , GARCIA GOMAR, Marta , ARTIAGA, Antonio Miguel
IPC分类号： G10L17/24 , G10L17/04 , G10L17/16 , G10L17/10
CPC分类号： G10L17/16 , G10L17/04 , G10L17/10 , G10L17/14 , G10L17/24 , G10L2015/025
摘要： Method for text-dependent Speaker Recognition using a speaker adapted Universal Background Model; wherein the speaker adapted Universal Background Model is a speaker adapted Hidden Markov Model comprising channel correction.
摘要翻译：使用扬声器适应通用背景模型的文本相关扬声器识别方法; 其中所述扬声器适配的通用背景模型是包括信道校正的扬声器适配的隐马尔可夫模型。

2. 发明申请

WO2014173919A1 ESTIMATION OF RELIABILITY IN SPEAKER RECOGNITION 审中-公开
标题翻译：扬声器识别的可靠性估计
公开(公告)号：WO2014173919A1
公开(公告)日：2014-10-30
申请号：PCT/EP2014/058174
申请日：2014-04-23
申请人： AGNITIO, S.L.
发明人： VAQUERO AVILÉS-CASCO, Carlos , BUERA RODRÍGUEZ, Luis , VILLALBA LÓPEZ, Jesús Antonio
IPC分类号： G10L17/06 , G10L17/20 , G10L17/04 , G10L17/10
CPC分类号： G10L17/10 , G10L15/01 , G10L15/083 , G10L17/04 , G10L17/06 , G10L17/12 , G10L17/20
摘要： A method for estimating the reliability of a result of a speaker recognition system concerning a testing audio and a speaker model, which is based on one, two, three or more model audios, the method using a Bayesian Network to estimate whether the result is reliable, wherein for estimating the reliability of the result of the speaker recognition system one, two, three, four or more than four quality measures of the testing audio and one, two, three, four or more than four quality measures of the model audio(s) are used.
摘要翻译：一种用于估计关于基于一个，两个，三个或更多个模型音频的测试音频和扬声器模型的说话者识别系统的结果的可靠性的方法，所述方法使用贝叶斯网络来估计结果是否可靠，其中为了估计所述说话人识别系统的结果的可靠性，所述测试音频的一个，二个，三个，四个或四个以上的质量测量和所述模型音频的一个，两个，三个，四个或多于四个的质量测量 s）。

3. 发明申请

WO2011066844A1 OBFUSCATED SPEECH SYNTHESIS 审中-公开
标题翻译： OBFUSCATED语音合成
公开(公告)号：WO2011066844A1
公开(公告)日：2011-06-09
申请号：PCT/EP2009/008596
申请日：2009-12-02
申请人： AGNITIO, S.L. , LANGEHOVEEN BRUMMER, Johan, Nikolaas , GLASSER, Avery, Maxwell , BUERA RODRIQUEZ, Luis
发明人： LANGEHOVEEN BRUMMER, Johan, Nikolaas , GLASSER, Avery, Maxwell , BUERA RODRIQUEZ, Luis
IPC分类号： G10L17/00 , G10L21/00
CPC分类号： G10L21/00 , G10L17/02
摘要： The present invention relates to a method for synthesizing a speech signal; comprising obtaining a speech sequence input signal comprising semantic content corresponding to a speaker's utterance; analyzing the input speech sequence signal to obtain a first sequence of feature vectors for the input speech sequence signal; synthesizing a second sequence of feature vectors different from and based on the first sequence of feature vectors; generating an excitation signal and filtering the excitation signal based on the second sequence of feature vectors to obtain a synthesized speech signal wherein the semantic content is obfuscated.
摘要翻译：本发明涉及一种用于合成语音信号的方法; 包括获得包括与说话者的话语对应的语义内容的语音序列输入信号; 分析输入语音序列信号以获得输入语音序列信号的第一特征向量序列; 合成不同于且基于第一特征向量序列的特征向量的第二序列; 产生激励信号，并且基于第二特征矢量序列对激励信号进行滤波，以获得语义内容被模糊化的合成语音信号。

4. 发明申请

WO2009098332A1 DISPOSITIVO DE RECONOCIMIENTO DE LOCUTOR 审中-公开
标题翻译：扬声器识别装置
公开(公告)号：WO2009098332A1
公开(公告)日：2009-08-13
申请号：PCT/ES2008/070020
申请日：2008-02-08
申请人： AGNITIO, S.L. , GARCÍA GOMAR, Marta , PALACIOS VENIN, Alicia
发明人： GARCÍA GOMAR, Marta , PALACIOS VENIN, Alicia
IPC分类号： G10L17/00
CPC分类号： G10L17/06
摘要： Dispositivo de reconocimiento de locutor que comprende, conectados en cascada, un módulo de extracción de coeficientes (11) que recibe una señal de audio mono (14), un módulo de fraccionamiento (22), un módulo de clasificación (23) y un módulo de cálculo de verosimilitud (24) que genera a 5 su salida (16) una media de las señales de verosimilitud relativas a las agrupaciones de fracciones generadas a la salida del clasificador (23).
摘要翻译：扬声器识别装置包括串联连接的系数提取模块（11），其接收单声道音频信号（14），分数模块（22），分类模块（23）和验证计算模块（24）在其输出端（16）处，与在分类器（23）处产生的分数组相关的检验信号的平均值输出。

5. 发明申请

WO2012175094A1 IDENTIFICATION OF A LOCAL SPEAKER 审中-公开
标题翻译：识别本地扬声器
公开(公告)号：WO2012175094A1
公开(公告)日：2012-12-27
申请号：PCT/EP2011/003034
申请日：2011-06-20
申请人： AGNITIO, S.L. , BUERA RODRIQUEZ, Luis , VAQUERO AVILES-CASCO, Carlos , GARCIA GOMAR, Marta
发明人： BUERA RODRIQUEZ, Luis , VAQUERO AVILES-CASCO, Carlos , GARCIA GOMAR, Marta
IPC分类号： G10L11/02 , G10L17/00 , G10L15/28
CPC分类号： G10L17/02 , G10L15/30 , G10L17/00 , G10L17/06 , G10L17/12 , G10L19/038 , G10L19/12 , G10L25/12 , G10L25/24 , G10L25/78
摘要： The present invention relates to a method for speaker identification, comprising the steps of detecting a (target) speaker's utterance locally; extracting features from the detected utterance locally; analyzing the extracted features in the local device to obtain information on the speaker identification and/or: encoding the extracted features locally; transmitting the encoded extracted features to a (remote) server; decoding and analyzing the received extracted features by the server to obtain information on the speaker identification; and transmitting the information on the speaker identification from the server to the location where the speaker's utterance was detected; and further comprising detecting locally speech activity and wherein the steps of extracting features and/or encoding the extracted features and/or transmitting the encoded extracted features to the server are only performed, if speech activity above some predetermined threshold is detected.
摘要翻译：本发明涉及一种用于说话者识别的方法，包括以下步骤：本地检测（目标）说话人的话语; 从本地检测到的话语中提取特征; 分析本地设备中提取的特征以获得关于说话者标识的信息和/或：在本地对所提取的特征进行编码; 将编码的提取的特征发送到（远程）服务器; 解码和分析由服务器接收的提取的特征以获得关于说话者识别的信息; 并将来自服务器的说话者识别信息发送到检测到说话人话语的位置; 并且还包括检测本地语音活动，并且其中仅当检测到高于某个预定阈值的语音活动时，才执行将提取的特征和/或编码所提取的特征和/或将编码的提取的特征发送到服务器的步骤。

6. 发明申请

WO2009124562A1 METHOD OF GENERATING A TEMPORARILY LIMITED AND/OR USAGE LIMITED MEANS AND/OR STATUS, METHOD OF OBTAINING A TEMPORARILY LIMITED AND/OR USAGE LIMITED MEANS AND/OR STATUS, CORRESPONDING SYSTEM AND COMPUTER READABLE MEDIUM 审中-公开
标题翻译：产生有限公司的方法和/或使用有限的方式和/或状态，获得有限公司的方法和/或使用有限的方式和/或状态，相关系统和计算机可读介质
公开(公告)号：WO2009124562A1
公开(公告)日：2009-10-15
申请号：PCT/EP2008/002777
申请日：2008-04-08
申请人： AGNITIO S.L. , MARTÍNEZ GUTIERREZ, Emilio
发明人： MARTÍNEZ GUTIERREZ, Emilio
IPC分类号： G07C9/00 , G10L17/00
CPC分类号： G07C9/00158 , G07C9/00563
摘要： The invention refers to a method of generating a means and/or status which is temporarily limited and/or usage limited and allows access to a service which has access restrictions, the method being carried out in a computing system and comprising the steps of establishing a telecommunications connection such that an audio call as for example a telephone call, within the telecommunications connection is preferably initiated by a person; determining biometric data of a specific person such as for example voice information; receiving data such as a voice utterance from the person which is connected by the telecommunications connection; verifying that the received data and the determined biometric data fit; and generating the means and/or status which is temporarily limited and/or usage limited after the verifying step.
摘要翻译：本发明涉及一种生成临时限制和/或使用受限的装置和/或状态的方法，并允许访问具有访问限制的服务，所述方法在计算系统中执行，并且包括以下步骤：建立电信连接，使得在电信连接内的音频呼叫例如电话呼叫优选地由个人发起; 确定特定人物的生物特征数据，例如语音信息; 从通过电话连接连接的人接收诸如语音话音的数据; 验证所接收的数据和所确定的生物特征数据是否适合; 并且在验证步骤之后生成临时限制和/或使用受限的装置和/或状态。

7. 发明申请

WO2011057650A1 SPEAKER RECOGNITION FROM TELEPHONE CALLS 审中-公开
标题翻译：扬声器从电话呼叫中识别
公开(公告)号：WO2011057650A1
公开(公告)日：2011-05-19
申请号：PCT/EP2009/008063
申请日：2009-11-12
申请人： AGNITIO, S.L. , LANGEHOVEEN BRUMMER, Johan, Nikolaas , BUERA RODRIGUEZ, Luis , GARCIA GOMAR, Marta
发明人： LANGEHOVEEN BRUMMER, Johan, Nikolaas , BUERA RODRIGUEZ, Luis , GARCIA GOMAR, Marta
IPC分类号： G10L17/00
CPC分类号： G10L17/02
摘要： The present invention relates to a method for speaker recognition, comprising the steps of obtaining and storing speaker information for at least one target speaker; obtaining a plurality of speech samples from a plurality of telephone calls from at least one unknown speaker; classifying the speech samples according to the at least one unknown speaker thereby providing speaker-dependent classes of speech samples; extracting speaker information for the speech samples of each of the speaker-dependent classes of speech samples; combining the extracted speaker information for each of the speaker-dependent classes of speech samples; comparing the combined extracted speaker information for each of the speaker-dependent classes of speech samples with the stored speaker information for the at least one target speaker to obtain at least one comparison result; and determining whether one of the at least one unknown speakers is identical with the at least one target speaker based on the at least one comparison result.
摘要翻译：本发明涉及一种用于说话者识别的方法，包括以下步骤：获取和存储至少一个目标说话者的说话者信息; 从至少一个未知扬声器的多个电话呼叫中获取多个语音样本; 根据至少一个未知扬声器对语音样本进行分类，从而提供说话者相关的语音样本类别; 提取每个说话者相关类别的语音样本的语音样本的说话者信息; 组合提取的说话者信息，用于每个说话者依赖类的语音样本; 将用于每个与扬声器相关的语音样本类别的提取的演讲人信息与用于所述至少一个目标讲话者的所存储的演讲者信息进行比较，以获得至少一个比较结果; 以及基于所述至少一个比较结果，确定所述至少一个未知扬声器中的一个是否与所述至少一个目标说话者相同。

8. 发明申请

WO2010066435A1 CUT AND PASTE SPOOFING DETECTION USING DYNAMIC TIME WRAPING 审中-公开
标题翻译：使用动态时间封装的切割和馅料检测
公开(公告)号：WO2010066435A1
公开(公告)日：2010-06-17
申请号：PCT/EP2009/008851
申请日：2009-12-10
申请人： AGNITIO S.L. , VILLALBA LÓPEZ, Jesús, Antonio , ORTEGA GIMÉNEZ, Alfonso , LLEIDA SOLANO, Eduardo , VARELA REDONDO, Sara , GARCĺA GOMAR, Marta
发明人： VILLALBA LÓPEZ, Jesús, Antonio , ORTEGA GIMÉNEZ, Alfonso , LLEIDA SOLANO, Eduardo , VARELA REDONDO, Sara , GARCĺA GOMAR, Marta
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 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由第一或第二语音话语的时间依赖特性和分别第二或第二语音话语的动态时间扭曲（202）时间依赖特性组成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发声的动态时间扭曲（202）时间依赖特性组成。

9. 发明申请

WO2009124563A1 METHOD OF INFORMING A PERSON OF AN EVENT AND METHOD OF RECEIVING INFORMATION ABOUT AN EVENT, A RELATED COMPUTING SYSTEM AND COMPUTER READABLE MEDIUM 审中-公开
标题翻译：通知事件的方法和接收关于事件的信息的方法，相关的计算系统和计算机可读介质
公开(公告)号：WO2009124563A1
公开(公告)日：2009-10-15
申请号：PCT/EP2008/002778
申请日：2008-04-08
申请人： AGNITIO, S.L. , GARCIA GOMAR, Marta
发明人： GARCIA GOMAR, Marta
IPC分类号： G06Q10/00
CPC分类号： G06Q10/00 , G10L17/00 , H04M3/53383 , H04M2201/41 , H04M2203/6045
摘要： The invention refers to a Method of informing a person of an event comprising carrying out in a computing system the steps of: receiving (10) information of an event (1); determining (11 ) a specific person which is to be notified of the event (1); performing (12) an information action with the aim of informing the specific person of the event (1 ) via a telecommunications system; receiving (15) a voice utterance of a person; verifying (16) that the identity of the person coincides with that of the specific person based on the received voice utterance using biometric voice data.
摘要翻译：本发明涉及一种向个人通知事件的方法，包括在计算系统中执行以下步骤：接收（10）事件（1）的信息; 确定（11）将被通知事件（1）的特定人; 执行（12）信息行动，目的是通过电信系统通知特定人事件（1）; 接收（15）一个人的声音; 使用生物特征语音数据验证（16）基于接收到的语音话语的人的身份与特定人的身份一致。

10. 发明申请

WO2007135218A1 PROCEDIMIENTO DE IDENTIFICACIÓN DE VOZ 审中-公开
标题翻译：语音识别方法
公开(公告)号：WO2007135218A1
公开(公告)日：2007-11-29
申请号：PCT/ES2007/070094
申请日：2007-05-18
申请人： AGNITIO, S.L. , CASTAÑO PEREA, JAVIER , MARTÍNEZ GUTIERREZ, Emilio , GARCÍA GOMAR, Marta
发明人： CASTAÑO PEREA, JAVIER , MARTÍNEZ GUTIERREZ, Emilio , GARCÍA GOMAR, Marta
IPC分类号： G10L17/00
CPC分类号： G10L17/06
摘要： Procedimiento de identificación de voz a partir de un conjunto de modelos de locutores diversos con distintas características, agrupados en clases de características similares. Una vez agrupados los modelos a partir de las distancias entre todos los posibles pares de modelos existentes en la situación inicial del conjunto de modelos, se evalúa la distancia de un nuevo modelo a una clase original seleccionada.
摘要翻译：基于具有不同特征的各种扬声器的一组模型的语音识别方法分类为类似特征的类别。一旦模型已经基于存在于模型集合的初始情况中的所有可能的模型对之间的距离被分组，则评估从新模型到所选原始类的距离。

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