公开(公告)号：US08972261B2

公开(公告)日：2015-03-03

申请号：US14171732

申请日：2014-02-03

Applicant: Intellisist, Inc.

Inventor： David Milstein

IPC: G10L15/00 ,  G10L15/06 ,  G10L15/26

CPC classification number: G10L15/26 ,  G10L15/01 ,  G10L15/06 ,  G10L15/063 ,  G10L15/10 ,  G10L15/1822 ,  G10L15/19 ,  G10L15/22 ,  G10L2015/0631 ,  G10L2015/0638 ,  H04M3/42221 ,  H04M3/51 ,  H04M3/5183

Abstract: A computer-implemented system and method for voice transcription error reduction is provided. Speech utterances are obtained from a voice stream and each speech utterance is associated with a transcribed value and a confidence score. Those utterances with transcription values associated with lower confidence scores are identified as questionable utterances. One of the questionable utterances is selected from the voice stream. A predetermined number of questionable utterances from other voice streams and having transcribed values similar to the transcribed value of the selected questionable utterance are identified as a pool of related utterances. A further transcribed value is received for each of a plurality of the questionable utterances in the pool of related utterances. A transcribed message is generated for the voice stream using those transcribed values with higher confidence scores and the further transcribed value for the selected questionable utterance.

Abstract translation: 提供了一种用于语音转录错误减少的计算机实现的系统和方法。 从语音流中获得语音话语，并且每个语音话语与转录值和置信度得分相关联。 具有与较低置信度得分相关联的转录值的话语被确定为可疑话语。 从语音流中选择一个可疑话语。 来自其他语音流并具有与所选择的可疑话语的转录值类似的转录值的预定数量的可疑话语被识别为相关话语池。 在相关话语池中的多个可疑话语中的每一个接收另外的转录值。 使用具有更高置信度得分的转录值和所选择的可疑话语的另外的转录值，为语音流生成转录消息。

公开(公告)号：US08948371B2

公开(公告)日：2015-02-03

申请号：US12039558

申请日：2008-02-28

Applicant: Gilad Odinak ,  Adam Waalkes

Inventor： Gilad Odinak ,  Adam Waalkes

IPC: H04M3/00 ,  H04M3/428 ,  H04M3/42 ,  H04M3/523

CPC classification number: H04M3/5175 ,  H04M3/42068 ,  H04M3/4285 ,  H04M3/5133 ,  H04M3/523 ,  H04M3/5238 ,  H04M2201/40

Abstract: A system and method for managing hold times during automated call processing is provided. A call is received from a caller and assigned to a call session. Data is obtained from the caller and evaluated for caller attributes related to the call session. Hold times are identified during the call session. Response content is customized for at least one of the hold times using the caller attributes. The customized response content is provided to the caller during that hold time.

Abstract translation: 提供了一种在自动呼叫处理期间管理保持时间的系统和方法。 来自呼叫者的呼叫被分配给呼叫会话。 从呼叫者获得数据，并评估与呼叫会话相关的呼叫者属性。 在呼叫会话期间确定保持时间。 使用呼叫者属性为至少一个保持时间定制响应内容。 定制的响应内容在保留时间内提供给呼叫者。

公开(公告)号：US08842811B2

公开(公告)日：2014-09-23

申请号：US13549101

申请日：2012-07-13

Applicant: Gilad Odinak ,  Thomas Veatch

Inventor： Gilad Odinak ,  Thomas Veatch

IPC: H04M1/64 ,  H04M3/51 ,  H04B1/38 ,  H04M3/523

CPC classification number: H04M3/5232 ,  G06F17/21 ,  G06Q10/063112 ,  G06Q10/1053 ,  G10L15/08 ,  G10L15/26 ,  G10L15/30 ,  G10L17/26 ,  G10L25/51 ,  G10L25/60 ,  H04M3/2281 ,  H04M3/51 ,  H04M3/5175 ,  H04M3/5233 ,  H04M3/5235 ,  H04M2201/40 ,  H04M2201/41 ,  H04M2203/402

Abstract: A computer-implemented system and method for providing recommendations for hiring agents within a call center environment is provided. A list of candidates for hire as agents within a call center is maintained. A voice recording from each of the candidates is analyzed by measuring voice characteristics within the voice recording and by calculating a score for the voice recording based on the measured voice characteristics. A threshold is applied to the voice recording score. One or more of the candidates on the list of candidates for hire is retained when the voice recording score for that candidate satisfies the threshold. One or more of the candidates from the list is removed when the voice recording score for that candidate fails to satisfy the threshold.

Abstract translation: 提供了一种用于在呼叫中心环境内为雇用代理提供建议的计算机实现的系统和方法。 保留在呼叫中心内作为代理人雇用的候选人名单。 通过测量语音记录中的语音特征，并通过基于所测量的语音特征来计算语音记录的得分来分析来自每个候选者的语音记录。 对录音分数应用阈值。 当候选人的录音分数满足阈值时，保留候选人候选人名单中的一个或多个候选人。 当该候选者的录音分数不能满足阈值时，该列表中的一个或多个候选者被移除。

公开(公告)号：US20140067390A1

公开(公告)日：2014-03-06

申请号：US14074653

申请日：2013-11-07

Applicant: Intellisist,Inc.

Inventor： Mike O. Webb

IPC: G10L15/26

CPC classification number: G10L15/26 ,  G10L15/04 ,  H04M3/53333 ,  H04M2201/40 ,  H04M2201/60 ,  H04M2203/2016 ,  H04M2203/4536

Abstract: A computer-implemented system and method for transcribing verbal messages is provided. Verbal messages each comprising audio content are received. Automatically recognized text is generated for the audio content of at least one of the verbal messages. A turn-around processing time is applied to the verbal message. The automatically recognized text and verbal message are transferred to a human agent when an expected processing time of the verbal message satisfies the turn-around processing time. At least a portion of the automatically recognized text is replaced with manual transcription from the human agent. The automatically recognized text and manual transcription are provided as a text message.

Abstract translation: 提供了一种用于转录口头消息的计算机实现的系统和方法。 接收包含音频内容的语音消息。 为至少一个口头消息的音频内容生成自动识别的文本。 翻译处理时间被应用于口头消息。 当语音消息的预期处理时间满足折返处理时间时，自动识别的文本和口头消息被传送到人类代理。 自动识别的文本的至少一部分被来自人类代理的手动转录替代。 自动识别的文本和手动转录作为文本消息提供。

公开(公告)号：US08521528B2

公开(公告)日：2013-08-27

申请号：US13526451

申请日：2012-06-18

Applicant: Gilad Odinak

Inventor： Gilad Odinak

IPC: G10L15/04

CPC classification number: G10L15/30 ,  G10L13/08 ,  G10L15/18 ,  G10L15/193 ,  G10L15/32 ,  G10L15/34 ,  H04M3/51 ,  H04M3/5166 ,  H04M3/5183 ,  H04M2201/38 ,  H04M2201/40

Abstract: A system and method for distributed speech recognition is provided. Audio data is obtained from a caller participating in a call with an agent. A main recognizer receives a main grammar template and the audio data. A plurality of secondary recognizers each receive the audio data and a reference that identifies a secondary grammar, which is a non-overlapping section of the main grammar template. Speech recognition is performed on each of the secondary recognizers and speech recognition results are identified by applying the secondary grammar to the audio data. An n number of most likely speech recognition results are selected. The main recognizer constructs a new grammar based on the main grammar template using the speech recognition results from each of the secondary recognizers as a new vocabulary. Further speech recognition results are identified by applying the new grammar to the audio data.

Abstract translation: 提供了一种用于分布式语音识别的系统和方法。 音频数据是从与代理商进行通话的主叫方获得的。 主识别器接收主语法模板和音频数据。 多个次级识别器各接收音频数据和标识辅助语法的参考，辅助语法是主语法模板的非重叠部分。 对每个二次识别器执行语音识别，并且通过将次要语法应用于音频数据来识别语音识别结果。 选择n个最可能的语音识别结果。 主识别器使用来自每个二级识别器的语音识别结果作为新词汇，基于主语法模板构建新的语法。 通过将新的语法应用于音频数据来识别进一步的语音识别结果。

公开(公告)号：US08462935B2

公开(公告)日：2013-06-11

申请号：US13371289

申请日：2012-02-10

Applicant: Gilad Odinak ,  Alastair Sutherland ,  William A. Tolhurst

Inventor： Gilad Odinak ,  Alastair Sutherland ,  William A. Tolhurst

IPC: H04M1/64 ,  G06F15/16

CPC classification number: H04M3/5166 ,  G10L15/26 ,  H04M3/51 ,  H04M3/5133 ,  H04M3/5183 ,  H04M3/5322 ,  H04M3/533 ,  H04M2201/38 ,  H04M2201/39 ,  H04M2201/40 ,  H04M2201/60 ,  H04M2203/306 ,  H04M2203/4536

Abstract: A system and method for monitoring an automated voice response (AVR) system is provided. An audio communication from a caller is processed by executing an AVR script with a plurality of instructions. A visual representation of the audio communication is presented to an agent substantially simultaneously with the audio communication based on the AVR script. The visual representation includes at least one field to be populated with information obtained from the caller and the information populated in the field can be updated by the agent.

Abstract translation: 提供了一种用于监视自动语音响应（AVR）系统的系统和方法。 通过执行具有多个指令的AVR脚本来处理来自呼叫者的音频通信。 音频通信的视觉表示基本上与基于AVR脚本的音频通信同时呈现给代理。 视觉表示包括至少一个要填充从呼叫者获得的信息的字段，并且可以由代理更新填充在该字段中的信息。

公开(公告)号：US20130064356A1

公开(公告)日：2013-03-14

申请号：US13669388

申请日：2012-11-05

Applicant: Intellisist, Inc.

Inventor： Adam Waalkes ,  Gilad Odinak ,  Haodong (Howard) Jiang ,  Matthew Thorn ,  Tom McCann

IPC: H04M1/64

CPC classification number: H04M3/42221 ,  H04M3/5166 ,  H04M3/5175 ,  H04M2203/301

Abstract: A system and method for storing call recordings in a call center is provided. Incoming calls to a call center are monitored. Retention criteria are obtained and ordered by importance. The retention criteria are applied to each of the calls. Those calls that match at least one of the retention criteria are identified. The identified calls that include one of a single highly important criteria and two or more less important criteria are selected for retaining in the call center. Recordings of the selected calls are stored in the call center.

Abstract translation: 提供了一种用于在呼叫中心存储呼叫记录的系统和方法。 对呼叫中心的来电进行监控。 保留条件是通过重要性获得和排序的。 保留条件适用于每个呼叫。 识别符合至少一个保留条件的呼叫。 选择包括单个非常重要的标准之一的标识呼叫和两个或更多不太重要的标准，以保留在呼叫中心。 所选呼叫的录音存储在呼叫中心。

公开(公告)号：US08023638B2

公开(公告)日：2011-09-20

申请号：US11893542

申请日：2007-08-15

Applicant: Adam Waalkes ,  Gilad Odinak ,  Haodong (Howard) Jiang ,  Matthew Thorn ,  Tom McCann

Inventor： Adam Waalkes ,  Gilad Odinak ,  Haodong (Howard) Jiang ,  Matthew Thorn ,  Tom McCann

IPC: H04M3/00 ,  H04M5/00

CPC classification number: H04M3/5234 ,  H04M3/5166

Abstract: A system and method for balancing agent console load during automated call processing is provided. A plurality of agent consoles are operated in a call center. Progress of a call session of a caller that is calling into the call center at each agent console is monitored. An absolute upper limit on a number of the call sessions allowed at each agent console at any given time is assigned. A load of call session assignments on each agent console is balanced. Objective and subjective conditions pertinent to each assigned call session are continually collected from each agent console. The objective and subjective conditions that affect call session availability are updated for each agent console. The objective and subjective conditions are evaluated against the absolute upper limit to determine a load factor. Each call session is assigned to one such agent console within bounds applicable to the load factor.

Abstract translation: 提供了一种用于在自动呼叫处理期间平衡代理控制台负载的系统和方法。 在呼叫中心中操作多个代理控制台。 监听在每个代理控制台呼入呼叫中心的呼叫者的呼叫进程进度。 分配在任何给定时间在每个代理控制台允许的呼叫会话数的绝对上限。 在每个代理控制台上加载一个呼叫会话分配是平衡的。 从每个代理控制台不断收集与每个分配的呼叫会话相关的目标和主观条件。 影响呼叫会话可用性的客观和主观条件将针对每个代理控制台进行更新。 根据绝对上限评估客观和主观条件以确定负载因子。 每个呼叫会话都分配给适用于负载因子的范围内的一个此类代理控制台。

公开(公告)号：US07996230B2

公开(公告)日：2011-08-09

申请号：US12462626

申请日：2009-08-06

Applicant: G. Kevin Doren

Inventor： G. Kevin Doren

IPC: G10L21/00 ,  H04N21/2389 ,  H04N21/435

CPC classification number: G06F21/32 ,  G06F21/6263 ,  G10L15/26 ,  G10L17/22 ,  G10L21/00 ,  H04M3/42221

Abstract: A marker is derived from an interaction between a person and an agent of a business and the agent's user interface. A part of a speech signal that corresponds to a portion of the person's special information is located with the marker. The speech signal results from the interaction between the person and the agent. The part of the speech signal that corresponds to the portion of the person's special information is rendered unintelligible.

Abstract translation: 标记来源于个人与企业的代理与代理的用户界面之间的交互。 对应于人的特殊信息的一部分的语音信号的一部分与标记位于一起。 语音信号是由人与代理人之间的相互作用产生的。 对应于该人的特殊信息的部分的语音信号的部分变得难以理解。

公开(公告)号：US07912512B2

公开(公告)日：2011-03-22

申请号：US10765720

申请日：2004-01-26

Applicant: Gilad Odinak

Inventor： Gilad Odinak

IPC: H04M1/00

CPC classification number: H04M1/6091 ,  H04L67/141 ,  H04L67/24 ,  H04M1/6075 ,  H04M2250/02 ,  H04W4/046 ,  H04W4/80 ,  H04W8/205 ,  H04W12/06

Abstract: A phone embedded within a vehicle for automatically using a service plan of a proximate personal mobile phone. The embedded phone includes an internal communication component that detects the presence of the personal mobile phone, and receives a mobile subscriber identification number from the detected phone. The embedded phone also includes an external communication component that sends the received mobile subscriber identification number to a wireless network authority, and receives an authentication request to the personal mobile phone via the embedded phone. The internal communication component sends the authentication request to the personal mobile phone. The personal mobile phone generates an authentication signal, and the external communication component sends the authentication signal to the wireless network authority.

Abstract translation: 嵌入在车辆内的用于自动使用邻近的个人移动电话的服务计划的电话。 嵌入式电话包括内部通信部件，其检测个人移动电话的存在，并从检测到的电话接收移动用户识别号码。 嵌入式电话还包括将接收的移动用户识别号码发送到无线网络机构的外部通信部件，并经由嵌入式电话机向个人移动电话机接收认证请求。 内部通信部件向个人手机发送认证请求。 个人移动电话产生认证信号，外部通信部件向无线网络机构发送认证信号。