公开(公告)号：US06996526B2

公开(公告)日：2006-02-07

申请号：US10040406

申请日：2002-01-02

申请人： Sara H. Basson ,  Peter Gustav Fairweather ,  Alexander Faisman ,  Dimitri Kanevsky ,  Jeffery Scott Sorensen

发明人： Sara H. Basson ,  Peter Gustav Fairweather ,  Alexander Faisman ,  Dimitri Kanevsky ,  Jeffery Scott Sorensen

IPC分类号： G10L15/00

CPC分类号： G10L15/32 ,  G10L15/30 ,  G10L17/00

摘要： A method and apparatus are disclosed for transcribing speech when a number of speakers are participating. A number of different speech recognition systems, each with a different speaker model, are executed in parallel. When the identity of all of the participating speakers is known and a speaker model is available for each participant, each speech recognition system employs a different speaker model suitable for a corresponding participant. Each speech recognition system decodes the speech and generates a corresponding confidence score. The decoded output having the highest confidence score is selected for presentation to a user. When all participating speakers are not known, or when there are too many participants to implement a unique speaker model for each participant, a speaker independent speech recognition system is employed together with a speaker specific speech recognition system. A controller selects between the decoded outputs of the speaker independent speech recognition system and the speaker specific speech recognition system based on information received from a speaker identification system and a speaker change detector.

公开(公告)号：US06988279B1

公开(公告)日：2006-01-17

申请号：US09580720

申请日：2000-05-30

申请人： Dimitri Kanevsky

发明人： Dimitri Kanevsky

IPC分类号： G06F7/04

CPC分类号： G06F21/6218 ,  G06F2221/2111

摘要： The authentication of intelligent agents (IA's) using a position locator system (PLS). Particularly contemplated is the comparison of the physical position of an intelligent agent requiring access to that of an intelligent agent whose identity is claimed by the former intelligent agent.

摘要翻译： 智能代理（IA）的使用位置定位系统（PLS）的认证。 特别考虑到需要访问的智能代理的物理位置与智能代理的物理位置的比较，该智能代理的身份由前智能代理要求保护。

公开(公告)号：US20050221268A1

公开(公告)日：2005-10-06

申请号：US10818656

申请日：2004-04-06

申请人： Jarir Chaar ,  Vincent Cina ,  Dimitri Kanevsky ,  Neal Keller ,  Juhnyoung Lee ,  Clifford Pickover ,  Edith Stern ,  Alexander Zlatsin

发明人： Jarir Chaar ,  Vincent Cina ,  Dimitri Kanevsky ,  Neal Keller ,  Juhnyoung Lee ,  Clifford Pickover ,  Edith Stern ,  Alexander Zlatsin

IPC分类号： G09B3/00 ,  G09B7/02

CPC分类号： G09B7/02

摘要： An adaptive system enables providers to customize educational objects and support services to maximize user engagement. The system is a self-service system for education for providers that includes a learning environment with interfaces for stakeholders, metrics for measuring the level of user engagement, and a customizable service configured to maximize user engagement. The system may operate in many domains, such as higher education, retail, government, test preparation and certification services, negotiations, and others.

摘要翻译： 自适应系统使提供商能够定制教育对象和支持服务，以最大限度地提高用户参与度。 该系统是供应商教育的自助服务系统，其中包括一个学习环境，为利益相关方提供界面，衡量用户参与度的度量标准，以及配置为最大化用户参与度的可定制服务。 该系统可以在许多领域运行，如高等教育，零售，政府，测试准备和认证服务，谈判等。

公开(公告)号：US06928031B1

公开(公告)日：2005-08-09

申请号：US09557119

申请日：2000-04-24

申请人： Dimitri Kanevsky ,  Wlodek Zadrozny

发明人： Dimitri Kanevsky ,  Wlodek Zadrozny

IPC分类号： G04B23/02 ,  G04C14/16

CPC分类号： A61B5/4812 ,  A61B5/11 ,  G06F19/00 ,  G06F19/3481

摘要： A programmable alarm clock system, method of operation and program product therefor with sleep analysis to identify and wake a person during non-REM sleep patterns, resulting in less subsequent drowsiness and better day-to-day functioning. The programmable alarm clock system includes at least one brain activity sensor attachable to a head of a sleeper. Brain activity signals from the sensor(s) are sent to a receiver at a local computer. The user, before retiring inputs a wake up time and attaches the sensor(s). The local computer sends brain activity signals to a remotely connected sleep analyzing server which analyzes the brain activity and identifies REM sleep periods and non-REM sleep periods. The labeled brain activity periods are returned to the local computer which waits for the wake up time. Then, the local computer sets an alarm time by adjusting the wake up time to coincide with a non-REM sleep period, if necessary and if possible. At the alarm time, the local computer sends a trigger to a remotely triggered local alarm device such as a clock, which sounds an alarm to wake the user/sleeper.

摘要翻译： 可编程闹钟系统，操作方法和程序产品，具有睡眠分析功能，可在非REM睡眠模式下识别和唤醒人员，从而减少随后的嗜睡和更好的日常功能。 可编程闹钟系统包括至少一个可移动到枕头头部的大脑活动传感器。 来自传感器的脑活动信号被发送到本地计算机的接收器。 用户在退出输入唤醒时间之前并附加传感器。 本地计算机将脑活动信号发送到远程连接的睡眠分析服务器，其分析大脑活动并识别REM睡眠期和非REM睡眠期。 标记的脑活动期返回到等待唤醒时间的本地计算机。 然后，如果需要，本地计算机通过调整唤醒时间来设置报警时间以与非REM休眠时段一致，并且如果可能的话。 在报警时，本地计算机向远程触发的本地报警设备（如时钟）发送触发信号，闹钟会唤醒用户/睡眠者。

公开(公告)号：US06919866B2

公开(公告)日：2005-07-19

申请号：US09777404

申请日：2001-02-06

申请人： Dimitri Kanevsky ,  Alexander Zlatsin

发明人： Dimitri Kanevsky ,  Alexander Zlatsin

IPC分类号： G01C21/36 ,  G02B27/00 ,  G02B27/01 ,  G09G5/00

CPC分类号： G01C21/365 ,  G02B27/01 ,  G02B27/0101 ,  G02B2027/014

摘要： A vehicular navigation system which utilizes an optical arrangement installed in eyeglasses or on the vehicle window or windshield so as to impart improved guiding directions to the vehicle. The navigation system enables a user to display their positional coordinates through the intermediary of a global positioning system (GPS) which communicates with a computer of the system. An additional element to current GPS (Global Positioning Systems), which utilizes an optical system located either on the windshield of a vehicle, such as an automobile or truck, or on the eyeglasses of a driver, or possibly on the windshield of an aircraft, which mimics an arrow pointing in the direction in the driver should be traveling.

摘要翻译： 一种车辆导航系统，其利用安装在眼镜或车窗或挡风玻璃上的光学装置，以便赋予车辆改进的引导方向。 导航系统使得用户能够通过与系统的计算机通信的全球定位系统（GPS）的中介来显示它们的位置坐标。 目前的GPS（全球定位系统）的一个附加元件，其利用位于诸如汽车或卡车的车辆的挡风玻璃上的驾驶员的眼镜，或者可能在飞机的挡风玻璃上的光学系统， 模仿一个指向司机方向的箭头应该是旅行。

公开(公告)号：US06820096B1

公开(公告)日：2004-11-16

申请号：US09707482

申请日：2000-11-07

申请人： Dimitri Kanevsky ,  Mariusz Sabath ,  Alexander Zlatsin

发明人： Dimitri Kanevsky ,  Mariusz Sabath ,  Alexander Zlatsin

IPC分类号： G06F1730

CPC分类号： G06Q10/109 ,  Y10S707/99945 ,  Y10S707/99952

摘要： The idea of this invention is to be able to create an external calendar that is connected to the Internet which can provide instant copies of the calendar, rewrite information on one calendar to another, and create a hassle free way to check calendar dates. One way this is done is by inserting a small digital chip into a calendar which allows the calendar to be connected to the Internet and to perform certain operations. The calendar will have a screen and a special digital pen which allows a user to fill in information (dates, events, appointments) into special date boxes.

摘要翻译： 本发明的想法是能够创建连接到互联网的外部日历，其可以提供日历的即时副本，将一个日历上的信息重写到另一个日历，并且创建一个无忧的方式来检查日历日期。 这样做的一个方法是将一个小型数字芯片插入一个日历，允许日历连接到互联网并执行某些操作。 日历将有一个屏幕和一个特殊的数字笔，允许用户将信息（日期，事件，约会）填写到特殊的日期框。

公开(公告)号：US06738535B2

公开(公告)日：2004-05-18

申请号：US09774489

申请日：2001-01-31

申请人： Dimitri Kanevsky ,  Jeffrey S. Sorensen

发明人： Dimitri Kanevsky ,  Jeffrey S. Sorensen

IPC分类号： H04N140

CPC分类号： G02B27/017

摘要： Apparatus, and associated methods, for transforming an image. The apparatus includes an aiming device to be aimed at an original stationary image, a transforming device which transforms the image into a revised image, and a displaying device which displays the revised image. The revised image may be related linguistically or pictographically to the original stationary image, or the revised image includes a label assigned to at least one pictographic property of the original stationary image. Uses of the apparatus include, but are not limited to, translating text from one language to another, simplifying text within the same language and labelling text with one or more pictographic icons. The apparatus can include glasses or goggles that are worn by a user and in which an image, corresponding to the revised image, is projected or displayed on at least one lens area.

摘要翻译： 装置和相关方法，用于转换图像。 该装置包括瞄准原始静止图像的瞄准装置，将图像变换成修正图像的变换装置，以及显示修正图像的显示装置。 修改后的图像可以与原始静止图像在语言上或图形上相关联，或者修改的图像包括分配给原始静止图像的至少一个图形属性的标签。 该装置的用途包括但不限于将文本从一种语言翻译成另一种语言，简化了相同语言中的文本，并用一个或多个象形图标标示文本。 该装置可以包括由用户佩戴的眼镜或护目镜，其中对应于修订图像的图像被投影或显示在至少一个透镜区域上。

公开(公告)号：US06665644B1

公开(公告)日：2003-12-16

申请号：US09371400

申请日：1999-08-10

申请人： Dimitri Kanevsky ,  Stephane Herman Maes ,  Jeffrey Scott Sorensen

发明人： Dimitri Kanevsky ,  Stephane Herman Maes ,  Jeffrey Scott Sorensen

IPC分类号： G10L1500

CPC分类号： G10L17/26 ,  H04M3/51 ,  H04M2201/40

摘要： A method for collecting data associated with the voice of a voice system user includes conducting a plurality of conversations with a plurality of voice system users. For each conversation, a speech waveform is captured and digitized, and at least one acoustic feature is extracted. The features are correlated with at least one attribute such as gender, age, accent, native language, dialect, socioeconomic classification, educational level and emotional state. Attribute data and at least one identifying indicia are stored for each user in a data warehouse, in a form to facilitate subsequent data mining thereon. The resulting collection of stored data is then mined to provide information for modifying underlying business logic of the voice system. An apparatus suitable for carrying out the method includes a dialog management unit, an audio capture module, an acoustic from end, a processing module and a data warehouse. Appropriate method steps can be implemented by a digital computer running a suitable program stored on a program storage device.

摘要翻译： 用于收集与语音系统用户的语音相关联的数据的方法包括与多个语音系统用户进行多个对话。 对于每个会话，语音波形被捕获并数字化，并且提取至少一个声学特征。 这些特征与至少一个属性（如性别，年龄，口音，母语，方言，社会经济分类，教育水平和情绪状态）相关联。 以数据仓库中的每个用户存储属性数据和至少一个识别标记，以便于其后面的数据挖掘。 然后，所得到的存储数据集合被开采以提供用于修改语音系统的底层业务逻辑的信息。 适用于执行该方法的装置包括对话管理单元，音频捕获模块，来自端部的声音，处理模块和数据仓库。 可以通过运行存储在程序存储设备上的合适程序的数字计算机来实现适当的方法步骤。

公开(公告)号：US06540674B2

公开(公告)日：2003-04-01

申请号：US09751531

申请日：2000-12-29

申请人： Wlodek W. Zadrozny ,  Dimitri Kanevsky

发明人： Wlodek W. Zadrozny ,  Dimitri Kanevsky

IPC分类号： A61B500

CPC分类号： A61B5/1113 ,  A61B5/0002 ,  A61B5/02055 ,  A61B5/7232 ,  A61B2560/0242

摘要： A system and method for supervising persons with a mental illness, the method comprising the steps of acquiring sensor data related to the person and the person's environment; tracking the acquired sensor data; and recognizing changes in the sensor data indicating the occurrence of an event. The method further comprises the steps of acquiring access to an event database of stored event data entries, each event data entry comprising identification of one of the sensor means, identification of the entity being sensed by the sensor means, and allowable values for the sensor data and recommendations for assistance providing actions to be taken when the received sensor data is out of range from the allowable sensor data; and recognizing the occurrence of an incident in which the received sensor data is outside of the range of the stored allowable sensor data values.

摘要翻译： 一种用于监督精神病患者的系统和方法，所述方法包括获取与人和人的环境有关的传感器数据; 跟踪获取的传感器数据; 以及识别表示事件发生的传感器数据的变化。 该方法还包括以下步骤：获取对存储的事件数据条目的事件数据库的访问，每个事件数据条目包括传感器装置之一的识别，由传感器装置感测的实体的识别以及传感器数据的允许值 以及关于当所接收的传感器数据超出允许的传感器数据超出范围时采取措施的辅助建议; 并且识别所接收的传感器数据在所存储的允许传感器数据值的范围之外的事件的发生。

公开(公告)号：US06484136B1

公开(公告)日：2002-11-19

申请号：US09422383

申请日：1999-10-21

申请人： Dimitri Kanevsky ,  Catherine G. Wolf ,  Wlodek W. Zadrozny

发明人： Dimitri Kanevsky ,  Catherine G. Wolf ,  Wlodek W. Zadrozny

IPC分类号： G06F1727

CPC分类号： G06F17/2765 ,  G06F17/28 ,  G10L2015/0631

摘要： A language recognition system, method and program product for recognizing language based input from computer users on a network of connected computers. Each computer includes at least one user based language model trained for a corresponding user for automatic speech recognition, handwriting recognition, machine translation, gesture recognition or other similar actions that require interpretation of user activities. Network computer users are clustered into classes of similar users according to user similarities such as, nationality, profession, sex, age, etc. User characteristics are collected by sensors and from databases and, then, distributed over the network during user activities. Language models with similarities among similar users on the network are identified. The language models include a language model domain, with similar language models being clustered according to their domains. Language models identified as similar are modified in response to user production activities. After modification of one language model, other identified similar language models are compared and adapted. Also, user data, including information about user activities and language model data, is transmitted over the network to other similar users. Language models are adapted only in response to similar user activities, when these activities are recorded and transmitted over the network. Language models are given a global context based on similar users that are connected together over the network.

摘要翻译： 用于在连接的计算机的网络上识别来自计算机用户的基于语言的输入的语言识别系统，方法和程序产品。 每个计算机包括针对用于自动语音识别，手写识别，机器翻译，手势识别或需要解释用户活动的其他类似动作的相应用户训练的至少一个基于用户的语言模型。 网络计算机用户根据用户的相似性（如国籍，职业，性别，年龄等）将类群集群分类。用户特征由传感器和数据库收集，然后在用户活动期间通过网络进行分发。 确定网络上类似用户之间具有相似性的语言模型。 语言模型包括语言模型域，其类似的语言模型根据其域名进行聚类。 识别为类似的语言模型是针对用户生产活动进行修改的。 在修改了一种语言模型后，对其他识别的类似语言模型进行了比较和修改。 此外，包括关于用户活动的信息和语言模型数据的用户数据通过网络发送到其他类似的用户。 当这些活动通过网络记录和传输时，语言模型仅适用于响应类似的用户活动。 基于通过网络连接在一起的类似用户，给予语言模型全局上下文。