公开(公告)号：US20150039304A1

公开(公告)日：2015-02-05

申请号：US14449770

申请日：2014-08-01

Applicant: Verint Systems Ltd.

Inventor： Ron Wein

IPC: G10L25/78

CPC classification number: G10L25/78

Abstract: Voice activity detection (VAD) is an enabling technology for a variety of speech based applications. Herein disclosed is a robust VAD algorithm that is also language independent. Rather than classifying short segments of the audio as either “speech” or “silence”, the VAD as disclosed herein employees a soft-decision mechanism. The VAD outputs a speech-presence probability, which is based on a variety of characteristics.

Abstract translation: 语音活动检测（VAD）是用于各种基于语音的应用的支持技术。 这里公开了一种也是语言无关的稳健的VAD算法。 而不是将音频的短片段分类为“语音”或“沉默”，因此本文所披露的VAD会雇用软判决机制。 VAD输出基于各种特征的语音存在概率。

公开(公告)号：US08948533B2

公开(公告)日：2015-02-03

申请号：US14264921

申请日：2014-04-29

Applicant: Verint Systems Ltd.

Inventor： Oren Golan ,  Itshak Horovitz

IPC: G06K9/42 ,  G06K9/40 ,  G06T7/00 ,  G06K9/00

CPC classification number: G06T7/0061 ,  G06K9/00369 ,  G06K9/00771 ,  G06K9/00778 ,  G06T5/005 ,  G06T5/30 ,  G06T7/194 ,  G06T7/536 ,  G06T2207/10016 ,  G06T2207/30196 ,  G06T2207/30232

Abstract: Systems, methods, and software for operating an image processing system are provided herein. In a first example, a method of operating an image processing system is provided. The method includes identifying object pixels associated with an object of interest in a scene, identifying additional pixels to associate with the object of interest, and performing an operation based on a depth of the object in the scene on target pixels comprised of the object pixels and the additional pixels to change a quality of the object of interest.

Abstract translation: 本文提供了用于操作图像处理系统的系统，方法和软件。 在第一示例中，提供了一种操作图像处理系统的方法。 该方法包括识别与场景中的感兴趣对象相关联的对象像素，识别与感兴趣对象相关联的附加像素，以及基于由对象像素组成的目标像素上的场景中的对象的深度来执行操作，以及 附加像素来改变感兴趣对象的质量。

公开(公告)号：US20140233803A1

公开(公告)日：2014-08-21

申请号：US14264943

申请日：2014-04-29

Applicant: Verint Systems Ltd.

Inventor： Oren Golan ,  Itshak Horovitz

IPC: G06T7/00 ,  G06K9/00

CPC classification number: G06T7/0061 ,  G06K9/00369 ,  G06K9/00771 ,  G06K9/00778 ,  G06T5/005 ,  G06T5/30 ,  G06T7/194 ,  G06T7/536 ,  G06T2207/10016 ,  G06T2207/30196 ,  G06T2207/30232

Abstract: Systems, methods, and software for operating an image processing system are provided herein. In a first example, a method of operating an image processing system is provided. The method includes identifying object pixels associated with an object of interest in a scene, identifying additional pixels to associate with the object of interest, and performing an operation based on a depth of the object in the scene on target pixels comprised of the object pixels and the additional pixels to change a quality of the object of interest.

公开(公告)号：US20140222419A1

公开(公告)日：2014-08-07

申请号：US14173435

申请日：2014-02-05

Applicant: Verint Systems Ltd.

Inventor： Roni Romano ,  Yair Horesh ,  Jeremie Dreyfuss

IPC: G06F17/27

CPC classification number: G06N5/022 ,  G06F16/367

Abstract: Systems and methods of automated ontology development include a corpus of communication data. The corpus of communication data includes communication data from a plurality of interactions and is processed. A plurality of terms are extracted from the corpus. Each term of the plurality is a plurality of words that identify a single concept within the corpus. An ontology is automatedly generated from the extracted terms.

Abstract translation: 自动本体发展的系统和方法包括通信数据语料库。 通信数据的语料库包括来自多个交互的通信数据并被处理。 从语料库中提取多个项。 多个的每个术语是识别语料库内的单个概念的多个单词。 从提取的术语中自动生成本体。

公开(公告)号：US20140214407A1

公开(公告)日：2014-07-31

申请号：US14167052

申请日：2014-01-29

Applicant: Verint Systems, Ltd.

Inventor： Yishay Yitshak

IPC: G06F17/28 ,  G06F17/27

CPC classification number: G06F17/2735 ,  G06F17/2775 ,  G06F17/30675 ,  G06F17/30985 ,  G06F21/55

Abstract: Methods and systems for keyword spotting, i.e., for identifying textual phrases of interest in input data. In the embodiments described herein, the input data comprises communication packets exchanged in a communication network. The disclosed keyword spotting techniques can be used, for example, in applications such as Data Leakage Prevention (DLP), Intrusion Detection Systems (IDS) or Intrusion Prevention Systems (IPS), and spam e-mail detection. A keyword spotting system holds a dictionary of textual phrases for searching input data. In a communication analytics system, for example, the dictionary defines textual phrases to be located in communication packets—such as e-mail addresses or Uniform Resource Locators (URLs).

Abstract translation: 用于关键字识别的方法和系统，即用于识别输入数据中感兴趣的文本短语。 在这里描述的实施例中，输入数据包括在通信网络中交换的通信分组。 所公开的关键字识别技术可以用于例如数据泄漏预防（DLP），入侵检测系统（IDS）或入侵防御系统（IPS）等应用以及垃圾邮件检测。 关键词发现系统持有用于搜索输入数据的文本短语字典。 在通信分析系统中，例如，字典定义要位于通信分组（例如电子邮件地址或统一资源定位符（URL））中的文本短语。

公开(公告)号：US20140201361A1

公开(公告)日：2014-07-17

申请号：US14195346

申请日：2014-03-03

Applicant: Verint Systems Ltd.

Inventor： Yuval Altman

IPC: H04L12/26

CPC classification number: H04L43/04 ,  H04L63/102 ,  H04L63/1408 ,  H04L67/306

Abstract: Methods and systems for identifying network users who communicate with the network (e.g., the Internet) via a given network connection. The disclosed techniques analyze traffic that flows in the network to determine, for example, whether the given network connection serves a single individual or multiple individuals, a single computer or multiple computers. A Profiling System (PS) acquires copies of data traffic that flow through network connections that connect computers to the WAN. The PS analyzes the acquired data, attempting to identify individuals who login to servers.

Abstract translation: 用于识别经由给定网络连接与网络（例如，因特网）通信的网络用户的方法和系统。 所公开的技术分析在网络中流动的流量，以例如确定给定的网络连接是否服务于单个个体或多个个体，单个计算机或多个计算机。 分析系统（PS）获取通过将计算机连接到WAN的网络连接流过的数据流量的副本。 PS分析所获得的数据，尝试识别登录到服务器的个人。

公开(公告)号：US20140177841A1

公开(公告)日：2014-06-26

申请号：US14058467

申请日：2013-10-21

Applicant: Verint Systems Ltd.

Inventor： Gideon Hazzani ,  Yoav Ariav

IPC: H04W12/04 ,  H04L29/06

CPC classification number: H04M3/2281 ,  H04L63/0428 ,  H04L63/0442 ,  H04L63/308 ,  H04M2201/41 ,  H04M2242/12 ,  H04M2242/30 ,  H04W4/025 ,  H04W12/02 ,  H04W12/04

Abstract: Methods and systems for monitoring, analyzing and acting upon voice calls in communication networks. An identification system receives monitored voice calls that are conducted in a communication network. Some of the monitored voice calls may be conducted by target individuals who are predefined as suspects. In order to maintain user privacy, the system selects and retains only voice calls that are suspected of being conducted by predefined targets. The techniques disclosed herein are particularly advantageous in scenarios where the network identifiers of the terminal used by the target are not known, or where the target uses public communication devices. In accordance with the disclosure, content-based identifiers such as speaker recognition or keyword matching are used.

Abstract translation: 在通信网络中监听，分析和处理语音呼叫的方法和系统。 识别系统接收在通信网络中进行的被监听的语音呼叫。 一些被监视的语音呼叫可以由预定义为嫌疑人的目标个人进行。 为了保持用户隐私，系统仅选择并保留被预先定义的目标涉嫌进行的语音通话。 本文公开的技术在目标使用的终端的网络标识符不知道或目标使用公共通信设备的情况下特别有利。 根据本公开，使用诸如说话者识别或关键字匹配之类的基于内容的标识符。

公开(公告)号：US20140142944A1

公开(公告)日：2014-05-22

申请号：US14084974

申请日：2013-11-20

Applicant: VERINT SYSTEMS LTD.

Inventor： Omer Ziv ,  Ran Achituv ,  Ido Shapira ,  Jeremie Dreyfuss

IPC: G10L17/00

CPC classification number: G10L17/005 ,  G10L17/02

Abstract: Systems and method of diarization of audio files use an acoustic voiceprint model. A plurality of audio files are analyzed to arrive at an acoustic voiceprint model associated to an identified speaker. Metadata associate with an audio file is used to select an acoustic voiceprint model. The selected acoustic voiceprint model is applied in a diarization to identify audio data of the identified speaker.

Abstract translation: 音频文件的系统和方法使用声学声纹模型。 分析多个音频文件以获得与所识别的说话者相关联的声学声波模型。 与音频文件相关联的元数据用于选择声学声纹模型。 所选择的声学声波模型被应用于二值化以识别所识别的扬声器的音频数据。

公开(公告)号：US20140112541A1

公开(公告)日：2014-04-24

申请号：US14145098

申请日：2013-12-31

Applicant: Verint Systems Ltd.

Inventor： Oren Golan ,  Shmuel Kiro ,  Itshak Horovitz

IPC: G06K9/00 ,  G06T5/00 ,  G06K9/46

CPC classification number: G06K9/00362 ,  G06K9/00281 ,  G06K9/4604 ,  G06K9/4609 ,  G06K9/522 ,  G06T5/00 ,  G06T7/13

Abstract: A method executed by a computer system for detecting edges comprises receiving an image comprising a plurality of pixels, determining a phase congruency value for a pixel, where the phase congruency value comprises a plurality of phase congruency components, and determining if the phase congruency value satisfies a phase congruency criteria. If the phase congruency value satisfies the phase congruency criteria, the computer system categorizes the pixel as an edge pixel. If the phase congruency value does not satisfy the phase congruency criteria, the computer system compares a first phase congruency component of the plurality of phase congruency components to a phase congruency component criteria. If the first phase congruency component satisfies the phase congruency component criteria, the computer system categorizes the pixel as an edge pixel, and if the first phase congruency component does not satisfy the phase congruency component criteria, categorizes the pixel as a non-edge pixel.

Abstract translation: 由计算机系统执行的用于检测边缘的方法包括：接收包括多个像素的图像，确定像素的相位一致值，其中相位一致值包括多个相位一致分量，以及确定相位一致值是否满足 阶段一致性标准。 如果相位一致值满足相位一致性标准，则计算机系统将像素分类为边缘像素。 如果相位一致值不满足相位一致性标准，则计算机系统将多个相位一致分量的第一相位一致分量与相位一致分量标准进行比较。 如果第一相位一致性分量满足相位一致分量标准，则计算机系统将像素分类为边缘像素，并且如果第一相位一致分量不满足相位一致分量标准，则将像素分类为非边缘像素。

公开(公告)号：US20140089498A1

公开(公告)日：2014-03-27

申请号：US13953090

申请日：2013-07-29

Applicant: Verint Systems Ltd.

Inventor： Eithan Goldfarb ,  Yishay Yitshak

IPC: H04L12/26

CPC classification number: H04L43/028 ,  H04L45/742 ,  H04L45/745 ,  H04L63/0263

Abstract: A rule engine configured with at least one hash table which summarizes the rules managed by the engine. The rule engine receives rules and automatically adjusts the hash table in order to relate to added rules and/or in order to remove cancelled rules. The adjustment may be performed while the rule engine is filtering packets, without stopping. The rules may be grouped into a plurality of rule types and for each rule type the rule engine performs one or more accesses to at least one hash table to determine whether any of the rules of that type match the packet. In some embodiments, the rule engine may automatically select the rule types responsive to a set of rules provided to the rule engine and adapt its operation to the specific rules it is currently handling, while not spending resources on checking rule types not currently used.

Abstract translation: 配置有至少一个哈希表的规则引擎，其总结由引擎管理的规则。 规则引擎接收规则并自动调整哈希表，以便与添加的规则相关联和/或为了删除已取消的规则。 可以在规则引擎正在过滤数据包而不停止的情况下执行调整。 规则可以被分组为多个规则类型，并且对于每个规则类型，规则引擎执行对至少一个哈希表的一个或多个访问，以确定该类型的任何规则是否与分组匹配。 在一些实施例中，规则引擎可以响应于提供给规则引擎的一组规则来自动选择规则类型，并且将其操作适应其当前正在处理的特定规则，同时不花费资源来检查当前未使用的规则类型。