利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

19 条记录 (耗时 0.025 秒)

    System and method for dynamic facial features for speaker recognition
    1.
    发明授权
    System and method for dynamic facial features for speaker recognition 有权
    用于说话者识别的动态面部特征的系统和方法

    公开(公告)号：US08897500B2

    公开(公告)日：2014-11-25

    申请号：US13101704

    申请日：2011-05-05

    申请人： Ann K. Syrdal ,  Sumit Chopra ,  Patrick Haffner ,  Taniya Mishra ,  Ilija Zeljkovic ,  Eric Zavesky

    发明人： Ann K. Syrdal ,  Sumit Chopra ,  Patrick Haffner ,  Taniya Mishra ,  Ilija Zeljkovic ,  Eric Zavesky

    IPC分类号： G06K9/00 ,  G10L17/24 ,  G06F21/32

    CPC分类号： G10L15/25 ,  G06F21/32 ,  G06F2221/2103 ,  G06K9/00255 ,  G06K9/00281 ,  G06K9/00288 ,  G06K9/00315 ,  G06K9/00335 ,  G10L17/24 ,  G10L21/06

    摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for performing speaker verification. A system configured to practice the method receives a request to verify a speaker, generates a text challenge that is unique to the request, and, in response to the request, prompts the speaker to utter the text challenge. Then the system records a dynamic image feature of the speaker as the speaker utters the text challenge, and performs speaker verification based on the dynamic image feature and the text challenge. Recording the dynamic image feature of the speaker can include recording video of the speaker while speaking the text challenge. The dynamic feature can include a movement pattern of head, lips, mouth, eyes, and/or eyebrows of the speaker. The dynamic image feature can relate to phonetic content of the speaker speaking the challenge, speech prosody, and the speaker's facial expression responding to content of the challenge.

    摘要翻译： 本文公开了用于执行说话者验证的系统，方法和非暂时的计算机可读存储介质。 被配置为实施该方法的系统接收到验证说话者的请求，产生对该请求是唯一的文本挑战，并且响应该请求提示说话者发出文本挑战。 然后当扬声器发出文本挑战时，系统记录扬声器的动态图像特征，并且基于动态图像特征和文本挑战来执行说话者验证。 录制扬声器的动态图像功能可以包括在说出文本挑战时录制扬声器的视频。 动态特征可以包括扬声器的头部，嘴唇，嘴巴，眼睛和/或眉毛的运动模式。 动态图像特征可以涉及讲话者讲话的语音内容，语音韵律以及响应于挑战内容的说话者的面部表情。

    SYSTEM AND METHOD FOR DYNAMIC FACIAL FEATURES FOR SPEAKER RECOGNITION
    2.
    发明申请
    SYSTEM AND METHOD FOR DYNAMIC FACIAL FEATURES FOR SPEAKER RECOGNITION 有权
    用于声音识别的动态特征的系统和方法

    公开(公告)号：US20120281885A1

    公开(公告)日：2012-11-08

    申请号：US13101704

    申请日：2011-05-05

    申请人： Ann K. SYRDAL ,  Sumit Chopra ,  Patrick Haffner ,  Taniya Mishra ,  Ilija Zeljkovic ,  Eric Zavesky

    发明人： Ann K. SYRDAL ,  Sumit Chopra ,  Patrick Haffner ,  Taniya Mishra ,  Ilija Zeljkovic ,  Eric Zavesky

    IPC分类号： G06K9/00

    CPC分类号： G10L15/25 ,  G06F21/32 ,  G06F2221/2103 ,  G06K9/00255 ,  G06K9/00281 ,  G06K9/00288 ,  G06K9/00315 ,  G06K9/00335 ,  G10L17/24 ,  G10L21/06

    摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media for performing speaker verification. A system configured to practice the method receives a request to verify a speaker, generates a text challenge that is unique to the request, and, in response to the request, prompts the speaker to utter the text challenge. Then the system records a dynamic image feature of the speaker as the speaker utters the text challenge, and performs speaker verification based on the dynamic image feature and the text challenge. Recording the dynamic image feature of the speaker can include recording video of the speaker while speaking the text challenge. The dynamic feature can include a movement pattern of head, lips, mouth, eyes, and/or eyebrows of the speaker. The dynamic image feature can relate to phonetic content of the speaker speaking the challenge, speech prosody, and the speaker's facial expression responding to content of the challenge.

    摘要翻译： 本文公开了用于执行说话者验证的系统，方法和非暂时的计算机可读存储介质。 被配置为实施该方法的系统接收到验证说话者的请求，产生对该请求是唯一的文本挑战，并且响应该请求提示说话者发出文本挑战。 然后当扬声器发出文本挑战时，系统记录扬声器的动态图像特征，并且基于动态图像特征和文本挑战来执行说话者验证。 录制扬声器的动态图像功能可以包括在说出文本挑战时录制扬声器的视频。 动态特征可以包括扬声器的头部，嘴唇，嘴巴，眼睛和/或眉毛的运动模式。 动态图像特征可以涉及讲话者讲话的语音内容，语音韵律以及响应于挑战内容的说话者的面部表情。

    System and method for generating challenge utterances for speaker verification
    3.
    发明授权
    System and method for generating challenge utterances for speaker verification 有权
    用于产生演讲者验证的挑战话语的系统和方法

    公开(公告)号：US09318114B2

    公开(公告)日：2016-04-19

    申请号：US12954094

    申请日：2010-11-24

    申请人： Ilija Zeljkovic ,  Taniya Mishra ,  Amanda Stent ,  Ann K. Syrdal ,  Jay Wilpon

    发明人： Ilija Zeljkovic ,  Taniya Mishra ,  Amanda Stent ,  Ann K. Syrdal ,  Jay Wilpon

    IPC分类号： G10L17/00 ,  G10L17/24 ,  G10L15/08 ,  G10L17/26

    CPC分类号： G10L17/24 ,  G10L15/02 ,  G10L15/08 ,  G10L17/00 ,  G10L17/04 ,  G10L17/26 ,  G10L2015/025

    摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media relating to speaker verification. In one aspect, a system receives a first user identity from a second user, and, based on the identity, accesses voice characteristics. The system randomly generates a challenge sentence according to a rule and/or grammar, based on the voice characteristics, and prompts the second user to speak the challenge sentence. The system verifies that the second user is the first user if the spoken challenge sentence matches the voice characteristics. In an enrollment aspect, the system constructs an enrollment phrase that covers a minimum threshold of unique speech sounds based on speaker-distinctive phonemes, phoneme clusters, and prosody. Then user utters the enrollment phrase and extracts voice characteristics for the user from the uttered enrollment phrase. The system generates a user profile, based on the voice characteristics, for generating random challenge sentences according to a grammar.

    摘要翻译： 本文公开了与说话者验证有关的系统，方法和非暂时的计算机可读存储介质。 在一个方面，系统从第二用户接收第一用户身份，并且基于身份访问语音特征。 该系统根据语音特征根据规则和/或语法随机生成挑战句，并提示第二用户说出挑战句。 系统验证第二用户是否是第一个用户，如果口头的挑战句子与语音特征相匹配。 在注册方面，系统构建了一个基于扬声器独特音素，音素集群和韵律，覆盖独特语音的最小阈值的注册短语。 然后用户发出注册短语，并从发出的注册短语中提取用户的语音特征。 该系统基于语音特征生成用户简档，用于根据语法产生随机挑战语句。

    SYSTEM AND METHOD FOR GENERATING CHALLENGE UTTERANCES FOR SPEAKER VERIFICATION
    4.
    发明申请
    SYSTEM AND METHOD FOR GENERATING CHALLENGE UTTERANCES FOR SPEAKER VERIFICATION 有权
    用于产生扬声器验证的挑战性的系统和方法

    公开(公告)号：US20120130714A1

    公开(公告)日：2012-05-24

    申请号：US12954094

    申请日：2010-11-24

    申请人： Ilija Zeljkovic ,  Taniya Mishra ,  Amanda Stent ,  Ann K. Syrdal ,  Jay Wilpon

    发明人： Ilija Zeljkovic ,  Taniya Mishra ,  Amanda Stent ,  Ann K. Syrdal ,  Jay Wilpon

    IPC分类号： G10L17/00 ,  G10L15/26

    CPC分类号： G10L17/24 ,  G10L15/02 ,  G10L15/08 ,  G10L17/00 ,  G10L17/04 ,  G10L17/26 ,  G10L2015/025

    摘要： Disclosed herein are systems, methods, and non-transitory computer-readable storage media relating to speaker verification. In one aspect, a system receives a first user identity from a second user, and, based on the identity, accesses voice characteristics. The system randomly generates a challenge sentence according to a rule and/or grammar, based on the voice characteristics, and prompts the second user to speak the challenge sentence. The system verifies that the second user is the first user if the spoken challenge sentence matches the voice characteristics. In an enrollment aspect, the system constructs an enrollment phrase that covers a minimum threshold of unique speech sounds based on speaker-distinctive phonemes, phoneme clusters, and prosody. Then user utters the enrollment phrase and extracts voice characteristics for the user from the uttered enrollment phrase. The system generates a user profile, based on the voice characteristics, for generating random challenge sentences according to a grammar.

    摘要翻译： 本文公开了与说话者验证有关的系统，方法和非暂时的计算机可读存储介质。 在一个方面，系统从第二用户接收第一用户身份，并且基于身份访问语音特征。 该系统根据语音特征根据规则和/或语法随机生成挑战句，并提示第二用户说出挑战句。 系统验证第二用户是否是第一个用户，如果口头的挑战句子与语音特征相匹配。 在注册方面，系统构建了一个基于扬声器独特音素，音素集群和韵律，覆盖独特语音的最小阈值的注册短语。 然后用户发出注册短语，并从发出的注册短语中提取用户的语音特征。 该系统基于语音特征生成用户简档，用于根据语法产生随机挑战语句。

    Verifying Transactions Using Out-of-Band Devices
    7.
    发明申请
    Verifying Transactions Using Out-of-Band Devices 有权
    使用带外设备验证事务

    公开(公告)号：US20120297476A1

    公开(公告)日：2012-11-22

    申请号：US13108561

    申请日：2011-05-16

    申请人： Ilija Zeljkovic ,  Juan Garay

    发明人： Ilija Zeljkovic ,  Juan Garay

    IPC分类号： G06F21/22

    CPC分类号： H04L63/1466 ,  H04L63/145 ,  H04L63/18

    摘要： The present disclosure relates to verifying transactions using user devices. A client device used to complete a transaction with a server computer. The client device communicates with a user device such as a smart phone, laptop computer, or other computing device. The user device communicates with the client device and a verification server via the out-of-band communication channel. The verification server receives two or more copies of session data associated with the transaction occurring between the client device and the server computer. One copy of the session data is received from the server computer and another copy of the session data is provided by the user device. The two copies of the session data are compared by the verification server or by the user device, and mismatches are reported as suspected malicious software attacks.

    摘要翻译： 本公开涉及使用用户设备验证事务。 用于与服务器计算机完成事务的客户端设备。 客户端设备与诸如智能电话，膝上型计算机或其他计算设备的用户设备进行通信。 用户设备经由带外通信信道与客户端设备和验证服务器进行通信。 验证服务器接收与在客户端设备和服务器计算机之间发生的事务相关联的会话数据的两个或多个副本。 从服务器计算机接收会话数据的一个副本，并且会话数据的另一副本由用户设备提供。 会话数据的两个副本由验证服务器或用户设备进行比较，不匹配被报告为可疑的恶意软件攻击。

    Method of speech recognition using decoded state sequences having constrained state likelihoods
    9.
    发明授权
    Method of speech recognition using decoded state sequences having constrained state likelihoods 失效
    使用具有约束状态似然性的解码状态序列的语音识别方法

    公开(公告)号：US5778341A

    公开(公告)日：1998-07-07

    申请号：US592751

    申请日：1996-01-26

    申请人： Ilija Zeljkovic

    发明人： Ilija Zeljkovic

    IPC分类号： G10L15/10 ,  G10L15/14 ,  G10L5/06

    CPC分类号： G10L15/144 ,  G10L15/10

    摘要： The invention is a speech recognition system and method for transmitting information including the receipt and decoding of speech information such as that modeled by hidden Markov models (HMMs). In this invention, the state likelihoods of the modeled state sequences contained within the speech information are assigned penalties based on the difference between those state likelihoods and a maximum possible state likelihood. Once penalties have been assigned, the modified state sequence with the modified state likelihoods having the highest cumulative state likelihoods is used in further speech recognition processing. In this manner, state sequences having no extremely poor state likelihoods are favored over those having both extremely high and extremely poor state likelihoods.

    摘要翻译： 本发明是用于发送包括诸如由隐马尔可夫模型（HMM）建模的语音信息的接收和解码的信息的语音识别系统和方法。 在本发明中，包含在语音信息内的建模状态序列的状态似然性基于这些状态似然性与最大可能状态似然性之间的差被分配惩罚。 一旦分配了处罚，则在进一步的语音识别处理中使用具有最高累积状态似然性的修正状态似然性的修改状态序列。 以这种方式，优于状态可能性极差的状态序列比具有极高状态可能性极差的状态序列更有利。