公开(公告)号：US09484035B2

公开(公告)日：2016-11-01

申请号：US14980934

申请日：2015-12-28

Applicant: Intellisist, Inc.

Inventor： Gilad Odinak

IPC: G10L15/30 ,  G10L15/32 ,  G10L15/34 ,  G10L15/193 ,  H04M3/51 ,  G10L15/18

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. A prompt is provided to a caller during a call. One or more audio responses are received from the caller in response to the prompt. Distributed speech recognition is performed on the audio responses by providing a non-overlapping section of a main grammar to each of a plurality of secondary recognizers for each audio response. Speech recognition is performed on the audio responses by each of the secondary recognizers using the non-overlapping section of the main grammar associated with that secondary recognizer. A new grammar is generated based on results of the speech recognition from each of the secondary recognizers. Further speech recognition is performed on the audio responses against the new grammar and a further prompt is selected for providing to the caller based on results of the distributed speech recognition.

Abstract translation: 提供了一种用于分布式语音识别的系统和方法。 在通话期间向呼叫者提供提示。 响应于提示，从呼叫者接收一个或多个音频响应。 通过向每个音频响应的多个次级识别器中的每一个提供主语法的非重叠部分来对音频响应执行分布式语音识别。 通过使用与该次要识别器相关联的主语法的非重叠部分的每个次级识别器对音频响应执行语音识别。 基于来自每个二级识别器的语音识别的结果生成新的语法。 对新语法的音频响应执行进一步的语音识别，并且基于分布式语音识别的结果，选择另外的提示来提供给呼叫者。

公开(公告)号：US09438734B2

公开(公告)日：2016-09-06

申请号：US11893552

申请日：2007-08-15

Applicant: Adam Waalkes ,  Alastair Sutherland ,  Gilad Odinak ,  Haodong (Howard) Jiang ,  Llance Kezner

Inventor： Adam Waalkes ,  Alastair Sutherland ,  Gilad Odinak ,  Haodong (Howard) Jiang ,  Llance Kezner

IPC: H04M3/00 ,  H04M3/523

CPC classification number: H04M3/5232 ,  H04M2203/2011

Abstract: A system and method for managing a dynamic call flow during automated call processing is provided. Calls from a plurality of callers into a call center are accommodated through monitored call sessions. A call flow for each call session is managed. Caller characteristics of the caller and physical conditions in relation to the call are evaluated. Those caller characteristics and physical conditions, which are respectively unique among the callers and the calls, are identified. The call flow of each call session is dynamically adjusted by modifying parameters for one or more of the caller characteristics and physical conditions. The caller characteristics, physical conditions, and parameters are stored in a database.

Abstract translation: 提供了一种用于在自动呼叫处理期间管理动态呼叫流的系统和方法。 通过监听的呼叫会话容纳来自多个呼叫者的呼叫进入呼叫中心。 管理每个呼叫会话的呼叫流程。 对呼叫者的呼叫者特征和与呼叫相关的物理条件进行评估。 识别呼叫者和呼叫中分别唯一的呼叫者特征和身体状况。 通过修改一个或多个呼叫者特征和物理条件的参数来动态调整每个呼叫会话的呼叫流程。 呼叫者的特征，物理条件和参数存储在数据库中。

公开(公告)号：US09392117B2

公开(公告)日：2016-07-12

申请号：US14668806

申请日：2015-03-25

Applicant: Intellisist, Inc.

Inventor： David Milstein ,  Gilad Odinak ,  Howard M. Lee

IPC: H04M3/00 ,  H04M5/00 ,  H04M3/523 ,  G06Q10/10

CPC classification number: H04M3/5191 ,  G06Q10/063112 ,  G06Q10/1097 ,  G10L25/87 ,  G10L2015/088 ,  H04M3/42221 ,  H04M3/5166 ,  H04M3/5175 ,  H04M3/5233 ,  H04M3/56 ,  H04M2201/40

Abstract: A computer-implemented call center architecture and method for optimizing customer experience through in-band expert intervention is provided. Calls conducted between an agent and a caller are monitored. A need for assistance by an expert agent in one such call based on an inquiry by the caller is identified. Expert selection criteria to a predetermined group of expert agents with expertise in subject matter relating to the caller's inquiry is applied. One of the expert agents that matches with the expert selection criteria is selected and a notification to the agent that the selected expert agent will assist with the call is transmitted. The expert agent is then patched into the call.

Abstract translation: 提供了一种通过带内专家干预优化客户体验的计算机实现的呼叫中心架构和方法。 监听代理和呼叫者之间进行的呼叫。 识别由基于呼叫者的查询的一个这样的呼叫中的专家代理的协助的需要。 应用专家选择标准给具有与呼叫者查询有关的主题的专业知识的预定专家组。 选择与专家选择标准相匹配的专家代理人之一，并且发送所选专家代理将协助该呼叫的代理通知。 然后将专家代理程序修补到呼叫中。

公开(公告)号：US09392108B2

公开(公告)日：2016-07-12

申请号：US14977549

申请日：2015-12-21

Applicant: Intellisist, Inc.

Inventor： David Milstein

IPC: G10L15/01 ,  G10L15/06 ,  G10L15/26 ,  H04M3/42 ,  G10L15/22 ,  H04M3/51

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 efficiently reducing transcription error during a call is provided. A group of similar questionable utterances is monitored. Each questionable utterance is assigned a transcribed value and is selected from a different call. A sample of the similar questionable utterances is selected from the group and provided to a human transcriber. A further transcribed value for each of the similar questionable utterances in the sample is received from the human transcriber. The further transcribed values for the similar questionable utterances in the sample are compared. Each of the remaining similar questionable utterances in the group are provided to the human transcriber when the compared further transcribed values of the similar questionable utterances in the sample are different.

Abstract translation: 提供了一种用于在呼叫期间有效降低转录错误的计算机实现的系统和方法。 监测一组类似的可疑话语。 每个可疑话语被分配一个转录的值，并从不同的呼叫中选择。 类似的可疑话语的样本从该组中选择并提供给人类誊写者。 来自人类誊写者的样本中的每个类似的可疑话语的另一转录值。 比较样本中类似可疑话语的进一步转录值。 当样本中相似的可疑话语的比较进一步转录值不同时，组中剩余的类似可疑话语中的每一个都提供给人类誊写者。

公开(公告)号：US09380161B2

公开(公告)日：2016-06-28

申请号：US14010471

申请日：2013-08-26

Applicant: Intellisist, Inc.

Inventor： Martin R. M. Dunsmuir

IPC: G10L15/00 ,  G10L25/00 ,  H04M3/493 ,  H04M7/00 ,  G10L15/26 ,  H04M3/533

CPC classification number: H04M3/4936 ,  G10L15/26 ,  H04M3/53325 ,  H04M3/53333 ,  H04M7/006 ,  H04M2201/40

Abstract: A computer-implemented system and method for user-controlled processing of audio signals is provided. An audio signal including a reference segment and a segment preceding the reference segment is obtained. A value q is received from a user. Audio buffers in the preceding segment are defined, each having a width of N samples and a starting point a unique number of samples away from the preceding segment's start, based on a division of N by q. One or more of the buffers are transformed into discrete Fourier transform (DFT) buffers. A signature of the signal is generated using at least a portion of the reference segment and at least one of the DFT buffers. A new audio signal is received and a DFT for the audio signal is generated. The new audio signal is determined to match the audio signal based on a comparison of the DFT to the signature.

Abstract translation: 提供了一种用于音频信号的用户控制处理的计算机实现的系统和方法。 获得包括参考段和参考段之前的段的音频信号。 从用户接收到值q。 定义前面段中的音频缓冲器，每个具有N个采样的宽度，并且起始点是离开前一段的开始的唯一的采样数，基于N除以q。 一个或多个缓冲器被转换成离散傅里叶变换（DFT）缓冲器。 信号的签名使用参考段的至少一部分和DFT缓冲器中的至少一个生成。 接收新的音频信号，并产生音频信号的DFT。 基于DFT与签名的比较，确定新音频信号以匹配音频信号。

公开(公告)号：US09218808B2

公开(公告)日：2015-12-22

申请号：US14636087

申请日：2015-03-02

Applicant: Intellisist, Inc.

Inventor： David Milstein

IPC: G10L15/01 ,  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 reducing voice transcription error is provided. Audio data is received during a call and parsed into utterances. A transcribed value and confidence score are assigned to each utterance. Those utterances with low confidence scores are identified as questionable utterances. One of the questionable utterances is selected from the audio data and a pool of questionable utterances is formed. The pool includes the selected questionable utterance and other questionable utterances, from other calls, that are similar to the selected questionable utterance. A size threshold is applied to the pool of questionable utterances. All the questionable utterances in the pool are provided to at least one human transcriber when the pool fails to satisfy the size threshold. Further transcribed values are received from the transcriber for each of the questionable utterances in the pool.

Abstract translation: 提供了一种用于减少语音转录错误的计算机实现的系统和方法。 音频数据在通话期间被接收并解析成话语。 转录的值和置信度得分分配给每个发音。 那些低置信度的话语被认为是可疑的话语。 从音频数据中选择可疑话语之一，并形成可疑话语池。 游泳池包括所选择的可疑话语和其他可疑话语，来自其他呼叫，类似于所选择的可疑话语。 大小阈值适用于可疑话语池。 当池不能满足大小阈值时，池中的所有可疑话语都提供给至少一个人转录器。 对于游泳池中的每个可疑话语，从抄录员收到进一步的转录值。

公开(公告)号：US08929516B2

公开(公告)日：2015-01-06

申请号：US14010510

申请日：2013-08-26

Applicant: Intellisist, Inc.

Inventor： Gilad Odinak

IPC: H04M1/64

CPC classification number: H04M3/53375 ,  H04L12/1822 ,  H04L12/1827 ,  H04L51/00 ,  H04L51/04 ,  H04L65/403 ,  H04M3/533 ,  H04M3/53333 ,  H04M3/53366 ,  H04M3/56 ,  H04M3/563 ,  H04M2203/4536 ,  H04M2203/5054 ,  H04M2207/18 ,  H04M2207/187 ,  H04W4/06 ,  H04W4/12 ,  H04W12/06

Abstract: A system and method for transmitting voice messages to a discussion group is provided. Users signed-on to a voice message server are identified. Each signed-on user is associated with one or more discussion groups and a personal communication device. The voice message server receives a voice message from one of the signed-on users via the personal communication device associated with that signed-on user and a discussion group to which the voice message is to be sent. The voice message from the signed-on user is provided to the other signed-on users in the discussion group.

Abstract translation: 提供了一种用于将语音消息发送到讨论组的系统和方法。 识别用户登录到语音留言服务器。 每个登录的用户与一个或多个讨论组和个人通信设备相关联。 语音消息服务器通过与该登录用户相关联的个人通信设备和要向其发送语音消息的讨论组从一个登录的用户接收语音消息。 来自登录用户的语音消息被提供给讨论组中的其他已登录的用户。

公开(公告)号：US08837687B2

公开(公告)日：2014-09-16

申请号：US13549238

申请日：2012-07-13

Applicant: Gilad Odinak ,  Thomas Veatch

Inventor： Gilad Odinak ,  Thomas Veatch

IPC: H04M1/64 ,  H04B1/38

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 matching agents with callers within a call center environment is provided. A database of traits for agents within a call center is maintained. A call is received into the call center and a voice recording is obtained from a caller during the call. The voice recording from the caller is analyzed by measuring voice characteristics of the voice recording and by identifying traits of the caller based on the voice characteristics. The caller traits are compared with the traits for the agents. One or more of the agents similar to the user are identified based on the trait comparison. One of the similar agents is selected and the call is transferred to the selected agent.

Abstract translation: 提供了一种用于在呼叫中心环境内与呼叫者匹配代理的计算机实现的系统和方法。 保持呼叫中心内代理人特征的数据库。 呼叫被接收到呼叫中心，并且在呼叫期间从呼叫者获得语音记录。 来自呼叫者的语音记录通过测量语音记录的语音特征和基于语音特征来识别呼叫者的特征来进行分析。 将呼叫者特征与代理的特征进行比较。 基于特征比较来识别与用户相似的一个或多个代理。 选择一个类似的代理，并将呼叫转移到所选代理。

公开(公告)号：US08645136B2

公开(公告)日：2014-02-04

申请号：US12840190

申请日：2010-07-20

Applicant: David Milstein

Inventor： David Milstein

IPC: G10L15/00 ,  G10L15/06

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 system and method for efficiently reducing transcription error using hybrid voice transcription is provided. A voice stream is parsed from a call into utterances. An initial transcribed value and corresponding recognition score are assigned to each utterance. A transcribed message is generated for the call and includes the initial transcribed values. A threshold is applied to the recognition scores to identify those utterances with recognition scores below the threshold as questionable utterances. At least one questionable utterance is compared to other questionable utterances from other calls and a group of similar questionable utterances is formed. One or more of the similar questionable utterances is selected from the group. A common manual transcription value is received for the selected similar questionable utterances. The common manual transcription value is assigned to the remaining similar questionable utterances in the group.

Abstract translation: 提供了一种使用混合语音转录有效降低转录错误的系统和方法。 一个语音流从一个电话解析为话语。 每个发音分配初始转录值和相应的识别分数。 为呼叫生成转录消息，并包括初始转录值。 将识别分数应用于阈值以将具有低于阈值的识别分数的话语识别为可疑话语。 将至少一个有问题的话语与其他电话的其他可疑话语进行比较，并形成一组类似的可疑话语。 从组中选择一个或多个相似的可疑话语。 对于所选择的类似的可疑话语，接收到常见的手动转录值。 常见的手动转录值被分配给组中剩余的类似的可疑话语。

公开(公告)号：US08520813B2

公开(公告)日：2013-08-27

申请号：US13544976

申请日：2012-07-09

Applicant: Gilad Odinak

Inventor： Gilad Odinak

IPC: H04M1/64

CPC classification number: H04M3/53375 ,  H04L12/1822 ,  H04L12/1827 ,  H04L51/00 ,  H04L51/04 ,  H04L65/403 ,  H04M3/533 ,  H04M3/53333 ,  H04M3/53366 ,  H04M3/56 ,  H04M3/563 ,  H04M2203/4536 ,  H04M2203/5054 ,  H04M2207/18 ,  H04M2207/187 ,  H04W4/06 ,  H04W4/12 ,  H04W12/06

Abstract: A system and method for transmitting voice messages via a centralized voice message server is provided. A plurality of communication devices are interfaced over a data network, and each communication device is associated with a user. At least one of the users is associated with a plurality of discussion groups. The user is identified as signed-in to two or more of the discussion groups. At least one of the two or more discussion groups to which the user is signed-in is identified as active. A voice message is received on a voice message server from the user. The voice message is transmitted to all members signed-in to the active discussion group from the voice message server. The voice message server further transmits voice messages to the user from members signed-in to the discussion groups to which the user is signed-in.

Abstract translation: 提供了一种通过集中语音消息服务器发送语音消息的系统和方法。 多个通信设备通过数据网络接口，并且每个通信设备与用户相关联。 至少一个用户与多个讨论组相关联。 用户被识别为两个或多个讨论组的登录。 用户登录的两个或多个讨论组中的至少一个被标识为活动的。 在来自用户的语音消息服务器上接收到语音消息。 语音消息被传送到从语音消息服务器登录到活动讨论组的所有成员。 语音消息服务器还通过登录到用户登录的讨论组的成员向用户发送语音消息。