利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

113 条记录 (耗时 0.036 秒)

    Testing acoustic echo cancellation and interference in VoIP telephones
    51.
    发明申请
    Testing acoustic echo cancellation and interference in VoIP telephones 有权
    测试VoIP电话中的回声消除和干扰

    公开(公告)号：US20080240370A1

    公开(公告)日：2008-10-02

    申请号：US11731956

    申请日：2007-04-02

    申请人： Kuansan Wang ,  Nirav Girish Shah

    发明人： Kuansan Wang ,  Nirav Girish Shah

    IPC分类号： H04M1/24

    CPC分类号： H04M1/2535 ,  H04M1/24

    摘要： Described is automatically testing the quality of an audio coupling between juxtaposed first and second digital telephones, e.g., VoIP telephones, such as to quantitatively determine the quality of audio echo cancellers in those digital telephones. An analyzer receives timestamps from a first telephone and second telephone during a calling session, including timestamps for when the second telephone initially provides audio (e.g., speech) to the first telephone, when the first telephone initially detects sound, when the first telephone initially provides audio to the second telephone, and when the second telephone initially detects sound. The analyzer uses the relative timing of the timestamps and the speech recognizer's outcome to determine whether the audio coupling is experiencing interference or echo. When the audio includes speech, a confidence level corresponding to accuracy of speech recognition also may establish the audio coupling's quality.

    摘要翻译： 所描述的是自动测试并置的第一和第二数字电话（例如VoIP电话）之间的音频耦合的质量，以便定量地确定那些数字电话中的音频回声消除器的质量。 分析仪在呼叫会话期间从第一电话和第二电话接收时间戳，包括当第一电话最初检测到声音时，当第一电话最初检测到声音时，第二电话最初向第一电话提供音频（例如，语音）的时间戳 音频到第二个电话，当第二个电话最初检测到声音时。 分析仪使用时间戳和语音识别器结果的相对定时来确定音频耦合是否正在经历干扰或回波。 当音频包括语音时，对应于语音识别精度的置信水平也可以建立音频耦合的质量。

    Secured communication via location awareness
    52.
    发明申请
    Secured communication via location awareness 有权
    通过位置感知进行安全通信

    公开(公告)号：US20080112551A1

    公开(公告)日：2008-05-15

    申请号：US11599647

    申请日：2006-11-14

    申请人： Scott C. Forbes ,  Linda Criddle ,  David Milstein ,  Lon-Chan Chu ,  Kuansan Wang ,  Michael D. Malueg

    发明人： Scott C. Forbes ,  Linda Criddle ,  David Milstein ,  Lon-Chan Chu ,  Kuansan Wang ,  Michael D. Malueg

    IPC分类号： H04M1/56

    CPC分类号： H04M3/42042 ,  H04L9/32 ,  H04L9/321 ,  H04M3/42034 ,  H04M3/436 ,  H04M2242/30 ,  H04W4/02 ,  H04W12/06 ,  H04W64/00 ,  H04W76/10

    摘要： A method and system for collecting and verifying the location information of a calling party and a device of the calling party is provided. More specifically, a method and system is provided for determining whether the identity of the calling party can be confirmed, via evaluating location information, with an acceptable degree of certainty. The location information may be provided by the calling party or obtained from various sources over a digital communication channel. Some of the provided location information which can be accidentally or intentionally altered is identified and evaluated to determine its accuracy as part of the verification process of the caller's identity.

    摘要翻译： 提供了一种用于收集和验证主叫方和主叫方的设备的位置信息的方法和系统。 更具体地，提供了一种方法和系统，用于通过以可接受的确定程度评估位置信息来确定主叫方的身份是否可以被确认。 位置信息可以由呼叫方提供或者通过数字通信信道从各种来源获得。 识别和评估可能意外或故意改变的一些提供的位置信息以确定其作为呼叫者身份的验证过程的一部分的准确性。

    Voicemail message controls
    53.
    发明申请
    Voicemail message controls 审中-公开
    语音邮件控件

    公开(公告)号：US20070280433A1

    公开(公告)日：2007-12-06

    申请号：US11444633

    申请日：2006-05-31

    申请人： David Milstein ,  David A. Howell ,  Kuansan Wang ,  Linda Criddle ,  Lon-Chan Chu ,  Michael D. Malueg

    发明人： David Milstein ,  David A. Howell ,  Kuansan Wang ,  Linda Criddle ,  Lon-Chan Chu ,  Michael D. Malueg

    IPC分类号： H04M1/64

    CPC分类号： H04M3/53341 ,  H04M3/5307 ,  H04M7/006 ,  H04M2201/42

    摘要： Generally described, aspects of the present invention are directed at software systems for responding to a received voicemail message. In one embodiment, a selection user interface is provided where a primary callee may generate an event to create a draft voicemail message that is related to a received voicemail message. In response to receiving an event from the selection user interface to create a draft voicemail message, aspects of the present invention (1) create an electronic file to store the draft voicemail message, and (2) insert metadata into the electronic file that defines the relationship between the draft voicemail message and the received voicemail message. As a result, a callee may easily create a draft voicemail message that is related to a received voicemail message and have the draft voicemail message automatically populated with contextual data.

    摘要翻译： 一般来说，本发明的方面涉及用于响应所接收的语音邮件消息的软件系统。 在一个实施例中，提供选择用户界面，其中主被叫方可以生成事件以创建与所接收的语音邮件消息相关的草稿语音邮件消息。 响应于从选择用户界面接收到创建草稿语音邮件消息的事件，本发明的方面（1）创建电子文件以存储草稿语音邮件消息，以及（2）将元数据插入到定义 语音留言信息和收到的语音邮件消息之间的关系。 因此，被叫方可以轻松地创建与接收到的语音邮件消息相关的草稿语音邮件消息，并且草稿语音邮件消息自动填充上下文数据。

    Mining data for services
    56.
    发明申请
    Mining data for services 有权
    挖掘服务数据

    公开(公告)号：US20070237149A1

    公开(公告)日：2007-10-11

    申请号：US11401022

    申请日：2006-04-10

    申请人： David Milstein ,  Kuansan Wang ,  Linda Criddle ,  Lon-Chan Chu ,  Michael Malueg ,  Scott Forbes

    发明人： David Milstein ,  Kuansan Wang ,  Linda Criddle ,  Lon-Chan Chu ,  Michael Malueg ,  Scott Forbes

    IPC分类号： H04L12/56

    CPC分类号： H04M3/2281 ,  G10L15/26 ,  H04L63/306 ,  H04M7/006

    摘要： Generally described, the present invention provides the ability to process digital voice conversations to identify data packets containing content of interest and to further process the identified data packets. More specifically, mining profiles may be developed identifying particular types of content that is to be mined and further identifying what is to be done when data packets containing such content is located. A system may search a digital voice conversation for the data packets containing the content and perform processing on the data packets once identified.

    摘要翻译： 通常描述，本发明提供处理数字语音对话以识别包含感兴趣内容的数据分组并进一步处理所识别的数据分组的能力。 更具体地，可以开发识别要被挖掘的特定类型的内容的挖掘简档，并且进一步识别当包含这样的内容的数据分组位于何时将要完成的内容。 系统可以搜索包含内容的数据分组的数字语音对话，并且对已经识别的数据分组执行处理。

    User authentication by combining speaker verification and reverse turing test
    57.
    发明申请
    User authentication by combining speaker verification and reverse turing test 有权

    公开(公告)号：US20060136219A1

    公开(公告)日：2006-06-22

    申请号：US11004548

    申请日：2004-12-03

    申请人： Kuansan Wang

    发明人： Kuansan Wang

    IPC分类号： G10L11/00

    CPC分类号： G06F21/31 ,  G06F21/32 ,  G10L17/22

    摘要： Methods and system for authenticating a user are disclosed. The present invention includes accessing a collection of personal information related to the user. The present invention also includes performing an authentication operation that is based on the collection of personal information. The authentication operation incorporates at least one dynamic component and prompts the user to give an audible utterance. The audible utterance is compared to a stored voiceprint.

    Integration of speech services with telecommunications
    58.
    发明申请
    Integration of speech services with telecommunications 有权

    公开(公告)号：US20060070081A1

    公开(公告)日：2006-03-30

    申请号：US10954676

    申请日：2004-09-30

    申请人： Kuansan Wang

    发明人： Kuansan Wang

    IPC分类号： G06F13/00

    CPC分类号： G06F8/00 ,  G06Q10/10

    摘要： A system for controlling a telephone infrastructure device or other network traffic service model based device includes an object oriented based application including a device object adapted for storing information pertaining to a physical or logical device, a call object adapted for storing information pertaining to a call between at least two device, a listener object adapted to provide speech recognition, a prompt object adapted to provide synthesized speech, and a connection object adapted for storing information pertaining to a connection between a call object and one of a device object, a listener object and a prompt object.

    Transcribing speech data with dialog context and/or recognition alternative information
    59.
    发明申请
    Transcribing speech data with dialog context and/or recognition alternative information 审中-公开
    用对话上下文和/或识别替代信息转录语音数据

    公开(公告)号：US20060004570A1

    公开(公告)日：2006-01-05

    申请号：US10880683

    申请日：2004-06-30

    申请人： Yun-Cheng Ju ,  Kuansan Wang ,  Siddharth Bhatia

    发明人： Yun-Cheng Ju ,  Kuansan Wang ,  Siddharth Bhatia

    IPC分类号： G10L15/06

    CPC分类号： G10L15/22 ,  G10L2015/228

    摘要： A framework for easy and accurate transcription of speech data is provided. Utterances related to a single task are grouped together and processed using combinations of associated sets of recognition results and/or context information in a manner that allows the same transcription for a selected recognition result to be assigned to each of the utterances under consideration.

    摘要翻译： 提供了一种简便准确地转录语音数据的框架。 与单个任务有关的语句被分组在一起，并使用相关联的识别结果集合和/或上下文信息的组合进行处理，以允许将所选择的识别结果相同的转录分配给所考虑的每个话语的方式。

    Methods and apparatus for decreasing the size of generated models trained for automatic pattern recognition
    60.
    发明授权
    Methods and apparatus for decreasing the size of generated models trained for automatic pattern recognition 失效
    用于减小自动模式识别训练的生成模型尺寸的方法和装置

    公开(公告)号：US5963902A

    公开(公告)日：1999-10-05

    申请号：US903477

    申请日：1997-07-30

    申请人： Kuansan Wang

    发明人： Kuansan Wang

    IPC分类号： G10L15/06 ,  G10L15/14 ,  G10L9/14

    CPC分类号： G06K9/6226 ,  G10L15/063 ,  G10L15/144

    摘要： Methods and apparatus for producing efficiently sized models suitable for pattern recognition purposes are described. Various embodiments are directed to the automated generation, evaluation, and selection of reduced size models from an initial model having a relatively large number of components, e.g., more components than can be stored for a particular intended application. To achieve model size reduction in an automated iterative manner, expectation maximization (EM) model training techniques are combined, in accordance with the present invention, with model size constraints. In one embodiment, a new reduced size model is generated using a LaGrange multiplier from an input model and input size constraints during each iteration of the size reducing model training process. The reduced size model generated during one iteration of the process serves as the input to the next iteration. Scoring, e.g., maximum likelihood scoring, and evaluation steps, in conjunction with stop criteria, are used to determine the number of model size reducing iterations performed, and which reduced size model is selected as the output of the size reduction model training process.

    摘要翻译： 描述了用于生产适合于图案识别目的的有效尺寸模型的方法和装置。 各种实施例涉及从具有相对大量组件的初始模型（例如，比可针对特定预期应用可以存储的组件更多的组件）自动生成，评估和选择减小尺寸模型。 为了以自动化迭代方式实现模型尺寸减小，根据本发明，将期望最大化（EM）模型训练技术与模型大小约束相结合。 在一个实施例中，使用来自输入模型的LaGrange乘法器生成新的缩小尺寸模型，并且在尺寸减小模型训练过程的每次迭代期间输入尺寸约束。 在该过程的一次迭代期间生成的缩小尺寸模型用作下一次迭代的输入。 使用结合停止标准的评分，例如最大似然评分和评估步骤来确定执行的减小迭代的模型大小的数量，并且选择哪种减小尺寸模型作为尺寸减小模型训练过程的输出。