公开(公告)号：US20160180835A1

公开(公告)日：2016-06-23

申请号：US14580331

申请日：2014-12-23

Applicant: NICE-SYSTEMS LTD

Inventor： Maor Nissan ,  Ronny Bretter

IPC: G10L15/06 ,  G10L15/02

CPC classification number: G10L15/063 ,  G10L15/187 ,  G10L2015/025 ,  G10L2015/0638

Abstract: A method for adapting a phonetic dictionary for peculiarities of a speech of an at least one speaker, comprising generating search pronunciations for a search term, retrieving audio sections from an audio database for each search pronunciation, audibly presenting to a person the audio sections of the speech of the at least one speaker, and updating the phonetic dictionary based on acceptability of the audio sections determined from judgments by the person regarding intelligibility of the audio sections in audibly pronouncing the provided at least one word, wherein the method is performed on an at least one computerized apparatus configured to perform the method.

Abstract translation: 一种用于对至少一个说话者的语音的特性进行适应语音字典的方法，包括产生用于搜索词语的搜索发音，从每个搜索发音的音频数据库检索音频部分，向人们呈现音频部分的音频部分 并且基于由人关于可听见地发音所提供的至少一个单词的音频部分的可懂度确定的音频部分的可接受性来更新语音字典，其中该方法在一个 配置为执行该方法的至少一个计算机化装置。

公开(公告)号：US20160171973A1

公开(公告)日：2016-06-16

申请号：US14571347

申请日：2014-12-16

Applicant: NICE-SYSTEMS LTD

Inventor： Maor NISSAN ,  Ronny BRETTER

IPC: G10L15/06

CPC classification number: G10L15/183 ,  G10L15/146 ,  G10L15/187

Abstract: A method for adapting a speech recognition system for out-of-vocabulary, comprising, decoding by a hybrid speech recognition a speech including out-of-vocabulary terms, thereby generating graphemic transcriptions of the speech with a mixture of recognized in-vocabulary words and unrecognized sub-words, while keeping a track of the decoded segments of the speech, determining in the transcription sequences of sub-words as candidate out-of-vocabulary words based on a first condition with respect to lengths of the sequences of sub-words and a second condition with respect to the number of repetitions of the sequences, audibly presenting to a user the candidate out-of-vocabulary words from the corresponding segments of the speech according to the track, and receiving from the user indications of valid words corresponding to audible presentations of the sequences of sub-words in the candidate out-of-vocabulary words, and training a speech recognition to additionally recognize the candidate out-of-vocabulary words, thereby adapting the speech recognition to recognize out-of-vocabulary words, wherein the method is performed on an at least one computerized apparatus configured to perform the method, and an apparatus for performing the same.

Abstract translation: 一种用于使语音识别系统适用于词汇外的方法，包括：通过混合语音识别解码包括词汇外的术语的语音，从而用识别的词汇单词的混合生成语音的字形转录;以及 无法识别的子词，同时保持语音的解码段的轨道，基于关于子词序列的长度的第一条件，将子词的转录序列确定为候选词外词 以及关于序列的重复次数的第二条件，根据该轨道向来自用户的语音的相应片段向用户可听地呈现候选的除了词汇词之外的条件，并且从用户接收对应的有效字的指示 对候选词外词语中的子词序列进行可听见的呈现，并且训练语音识别以另外识别候选词o 从而使语音识别适应于识别超出词汇的单词，其中该方法在被配置为执行该方法的至少一个计算机化设备上执行，以及用于执行该方法的设备。

公开(公告)号：US09369570B1

公开(公告)日：2016-06-14

申请号：US14714374

申请日：2015-05-18

Applicant: NICE-SYSTEMS LTD

Inventor： Efim Kolodizner ,  Shay Levy ,  Tal Zur ,  Roni Krivoshey ,  Kobi Shem Tov

IPC: H04M1/24 ,  H04M3/08 ,  H04M3/22 ,  H04M3/42 ,  H04M1/656

CPC classification number: H04M3/2236 ,  H04M1/656 ,  H04M3/42221

Abstract: A method comprising that in response to a beginning of a telephonic interaction in a local telephony system concurrently activating recordations of the telephonic interaction in a plurality of recorders operative parallelly and independently to obtain a plurality of recordings of the interaction corresponding to the plurality of recorders, and further in response to an ending of the telephonic interaction in the local telephony system concurrently terminating the recordations of the telephonic interaction in the plurality of the recorders, thereby providing the plurality of recordings of the interaction corresponding to the plurality of recorders, and subsequently selecting at least one recording among the plurality of the recordings of the interaction based on acquired data related to the quality of recordings associated the recordations, and an apparatus for performing the same.

Abstract translation: 一种方法，包括响应于本地电话系统中的电话交互的开始，同时激活多个记录器中的电话交互的记录并且独立地操作以获得与多个记录器相对应的交互的多个记录， 并且还响应于本地电话系统中的电话交互的结束同时终止多个记录器中的电话交互的记录，从而提供与多个记录器相对应的交互的多个记录，并随后选择 基于与记录关联的记录的质量相关的获取的数据，在多个记录中的至少一个记录，以及用于执行该记录的装置。

公开(公告)号：US20160048546A1

公开(公告)日：2016-02-18

申请号：US14639152

申请日：2015-03-05

Applicant: NICE-SYSTEMS LTD

Inventor： Hila WEISMAN ,  Peter Izsak ,  Victor Shafran

IPC: G06F17/30 ,  G10L15/02 ,  G06F17/27

CPC classification number: G06F17/30345 ,  G06F17/2765 ,  G06F17/2785 ,  G06F17/3056 ,  G06F17/30876 ,  G10L15/02

Abstract: A method for determining prominent keyphrases in interactions, comprising, receiving keyphrases of numerous interactions received via a plurality of channels that comprise apparatuses for conveying the interactions according to the media thereof, quantitatively evaluating each keyphrase by a plurality of different metrics thereby yielding a corresponding plurality of values, and linearly combining the plurality of the values with a corresponding plurality of coefficients associated with a channel via which an interaction having said keyphrase is received, thereby providing a score of said keyphrase, and based on a condition related to the scores of the keyphrases, selecting at least one keyphrase as an at least one prominent keyphrase, wherein the method is at least partially performed by an at least one computerized apparatus configured for interfacing with the apparatuses of the plurality of the channels.

Abstract translation: 一种用于确定交互中突出的关键短语的方法，包括：接收经由多个信道接收的许多交互的关键短语，所述多个交互包括根据其媒体传送交互的装置，通过多个不同的度量定量地评估每个关键短语，从而产生相应的多个 并且将所述多个值线性组合为与通过该相关联的频道相关联的相应多个系数，通过该频道接收具有所述关键词的交互，从而提供所述关键词的分数，并且基于与所述关键词的分数相关的条件 关键短语，选择至少一个关键短语作为至少一个突出的关键短语，其中所述方法至少部分地由被配置为与所述多个频道的装置进行接口的至少一个计算机化装置执行。

公开(公告)号：US20150278192A1

公开(公告)日：2015-10-01

申请号：US14224086

申请日：2014-03-25

Applicant: NICE-SYSTEMS LTD

Inventor： Ronny Bretter ,  Shimrit Artzi ,  Maor Nissan

IPC: G06F17/27 ,  G06F17/28

CPC classification number: G10L15/00 ,  G06F17/2785 ,  G10L15/065 ,  G10L15/183

Abstract: A method for adapting a language model for a context of a domain, comprising obtaining textual contents from a large source by a request directed to the context of the domain, discarding at least a part of the textual contents that contain textual terms determined as irrelevant to the context of the domain, thereby retaining, as retained data, at least a part of the textual contents that contain textual terms determined as relevant to the context of the domain, and adapting the language model by incorporating therein at least a part of the textual terms of the retained data, wherein the method is performed on an at least one computerized apparatus configured to perform the method and equipped for communication with the large source, and an apparatus for performing the same.

Abstract translation: 一种用于适应域的上下文的语言模型的方法，包括通过针对所述域的上下文的请求从大来源获取文本内容，丢弃包含被确定为不相关的文本术语的文本内容的至少一部分 从而保留作为保留数据的文本内容的至少一部分文本内容，该文本内容包含与域的上下文相关的文本术语，并且通过在其中并入至少一部分文本来适应语言模型 所述保留数据的条件，其中，所述方法在被配置为执行所述方法并被配备为与所述大源进行通信的至少一个计算机化装置上执行，以及用于执行所述方法的装置。

公开(公告)号：US20150227437A1

公开(公告)日：2015-08-13

申请号：US14176346

申请日：2014-02-10

Applicant: NICE-SYSTEMS LTD.

Inventor： Dan EIDELMAN

IPC: G06F11/14 ,  G06F11/30 ,  G06F11/20

CPC classification number: G06F11/1456 ,  G06F11/008 ,  G06F11/1662 ,  G06F11/201 ,  G06F11/2069 ,  G06F11/2094 ,  G06F11/3034 ,  G06F11/3055 ,  G06F11/3419 ,  G06F11/3485 ,  G06F2201/81 ,  G06F2201/84

Abstract: A system and method for managing storage of a digital stream including writing data of the stream to a network storage device, while monitoring availability of the network storage device, switching to writing additional data of the stream to a standby storage device while continuing monitoring the availability of the network storage device, if the network storage device becomes unavailable, switching back to writing additional data of the stream to the network storage device while continuing monitoring the availability of the network storage device, when the network storage device becomes available, and writing to the network storage device the additional data that was written to the standby storage device while the network storage device was unavailable, concurrently with the writing of the additional data of the stream to the network storage device.

Abstract translation: 一种用于管理数字流的存储的系统和方法，包括将流的数据写入网络存储设备，同时监视网络存储设备的可用性，切换将流的附加数据写入备用存储设备，同时继续监视可用性 的网络存储装置，如果网络存储装置变得不可用，则在网络存储装置变得可用时继续监视网络存储装置的可用性，切换回到向网络存储装置写入流的附加数据，并写入 网络存储设备在网络存储设备不可用时写入备用存储设备的附加数据与将流的附加数据写入网络存储设备同时进行。

公开(公告)号：US09098724B2

公开(公告)日：2015-08-04

申请号：US14104609

申请日：2013-12-12

Applicant: NICE-SYSTEMS LTD.

Inventor： Oren Keidar ,  Ran Bar-Sella ,  Igal Dvir

IPC: G06F21/64 ,  G06F21/60

CPC classification number: G06F21/64 ,  G06F21/60 ,  G06F21/602 ,  G06T1/0021 ,  H04N5/913 ,  H04N9/8042 ,  H04N19/467 ,  H04N2005/91335 ,  H04N2005/91364

Abstract: A method for verifying the authenticity and integrity of an ordered sequence of digital video frames, without having access to the original recording, by embedding therein a respective series of digital signatures based on a secret key, or keys, and on the video content of respective frames. Signatures are camouflaged by embedding in transform coefficients of a transformed representation of the video data in parts of the frame corresponding to motion. If there is sufficient motion to contain all of the signature bits, a supplementary technique embeds in high-texture areas of a frame. A final fall-back is to embed in a pre-defined default zone. A method of predicting when supplementary embedding is needed enables the process to be applied in a single pass allowing real-time operation. Verification is done during decoding by comparing, for identity, embedded signatures with signatures calculated anew using the method employed to embed.

Abstract translation: 一种用于通过在其中嵌入基于秘密密钥或密钥的相应系列数字签名以及相应的视频内容来验证数字视频帧的有序序列的真实性和完整性的方法，而不访问原始记录 框架。 通过在对应于运动的帧的部分中嵌入视频数据的变换表示的变换系数来伪装签名。 如果存在足够的运动以包含所有签名比特，则补充技术嵌入在帧的高纹理区域中。 最后的回落是嵌入预定义的默认区域。 一种预测何时需要补充嵌入的方法可以使该过程以一次通过，从而实现实时操作。 在解码过程中，通过比较嵌入式签名与使用嵌入方法重新计算的签名，进行解码时的验证。

公开(公告)号：US08948565B2

公开(公告)日：2015-02-03

申请号：US14010556

申请日：2013-08-27

Applicant: Nice-Systems Ltd

Inventor： Sergey Pashkevich ,  Doron Girmonsky ,  Yaron Shmueli ,  Meir Bechor

IPC: H04N5/765 ,  H04N9/80 ,  H04N5/92 ,  H04N5/917 ,  H04N5/91 ,  H04N7/18 ,  H04N9/804 ,  H04N21/231 ,  H04N21/2747 ,  H04N9/79 ,  H04N9/82

CPC classification number: H04N5/917 ,  H04N5/765 ,  H04N5/91 ,  H04N7/181 ,  H04N9/7921 ,  H04N9/8042 ,  H04N9/8205 ,  H04N21/23113 ,  H04N21/2747

Abstract: The subject matter discloses a method, comprising obtaining a current retention time of storage associated with a digital recorder; obtaining current bitrates of channels used to transmit video captured by edge devices communicating with the digital recorder. The method then determines change in compression rates to be allocated to at least a portion of the channels according to the current retention time and the current bitrates and transmits the change in compression rates to be allocated to the channels to edge devices communicating with the digital recorder. The method can be implemented in a system in which several digital recorders use the same storage.

Abstract translation: 该主题公开了一种方法，包括获得与数字记录器相关联的存储器的当前保留时间; 获得用于传输与数字记录器通信的边缘设备捕获的视频的信道的当前比特率。 然后，该方法根据当前保持时间和当前比特率确定要分配给至少一部分信道的压缩率的变化，并将要分配给该信道的压缩率变化发送到与数字录像机通信的边缘设备 。 该方法可以在几个数字记录器使用相同存储器的系统中实现。

公开(公告)号：US20140298346A1

公开(公告)日：2014-10-02

申请号：US13944881

申请日：2013-07-18

Applicant: NICE-SYSTEMS LTD.

Inventor： Eli ZAKASHANSKY ,  Roni Krivoshey ,  Efim Kolodizner ,  Uzi Baruch ,  Karawan Shorosh ,  Shlomi Haba

IPC: G06F9/50

CPC classification number: G06F9/5033

Abstract: A system and method for management of task allocation in a multi-core processing system. A controller of the processing unit may, at an initialization stage determine a number of worker threads to be a prime number not smaller than a multiplication of the number of the processing cores and a predetermined factor, assign a worker identification number (ID) to each worker thread, wherein the worker IDs are consecutive positive integers ranging from zero to the number of workers minus one. At a processing state the controller may receive from a dispatcher of the processing system a task associated with a numeric context ID and designate the task to one of the worker threads, wherein the worker ID of the designated worker thread equals the numeric context ID of the task, modulo the number of worker threads.

Abstract translation: 一种用于管理多核处理系统中任务分配的系统和方法。 处理单元的控制器可以在初始化阶段将工作线程的数量确定为不小于处理核心数量和预定因子的素数的素数，将工作人员标识号（ID）分配给每个 工作线程，其中工作者ID是从零到工人数减1之间的连续正整数。 在处理状态下，控制器可以从处理系统的调度器接收与数字上下文ID相关联的任务，并将任务指定给工作线程之一，其中指定的工作线程的工作者ID等于 任务，模数工作线程数。

公开(公告)号：US20130142318A1

公开(公告)日：2013-06-06

申请号：US13748658

申请日：2013-01-24

Applicant: NICE-SYSTEMS LTD.

Inventor： Stas MARGOLIS ,  Leon Portman ,  Mordehai Cory

IPC: H04M3/42

CPC classification number: H04M3/42221 ,  H04L63/08 ,  H04L67/1034 ,  H04L67/1089 ,  H04L67/1093

Abstract: System and method for recording communication sessions in a peer-to-peer communication networks. A conference call may be established between an external end-device, a target agent end-device of a call center and a recorder over a peer-to-peer communication network. After the conference call is established, the recorder may receive media transferred between the external end-device and the target agent end-device and record that media.

Abstract translation: 用于在对等通信网络中记录通信会话的系统和方法。 在外部终端设备，呼叫中心的目标代理终端设备和对等通信网络上的记录器之间可建立电话会议。 在电话会议建立之后，录音机可以接收在外部终端设备和目标代理终端设备之间传送的媒体并记录该媒体。