公开(公告)号：US07660719B1

公开(公告)日：2010-02-09

申请号：US10922433

申请日：2004-08-19

申请人： Bertrand A. Damiba ,  Rohit Dhawan ,  Navneet Raja ,  Anthony Rajakumar ,  Vipul Niranjan Vyas

发明人： Bertrand A. Damiba ,  Rohit Dhawan ,  Navneet Raja ,  Anthony Rajakumar ,  Vipul Niranjan Vyas

IPC分类号： G10L15/00

CPC分类号： H04M3/4938 ,  G06Q10/10 ,  H04M3/493 ,  H04M2201/40 ,  H04M2203/2061

摘要： A system, method and computer program product are provided for collecting information utilizing speech recognition. After receiving a specification, a voice application is configured based on the specification. During use, the voice application is capable of collecting information utilizing speech recognition.

摘要翻译： 提供了一种系统，方法和计算机程序产品，用于收集利用语音识别的信息。 接收到规格后，根据规格配置语音应用程序。 在使用过程中，语音应用能够利用语音识别来收集信息。

公开(公告)号：US20070282605A1

公开(公告)日：2007-12-06

申请号：US11754974

申请日：2007-05-29

申请人： Anthony Rajakumar

发明人： Anthony Rajakumar

IPC分类号： G10L15/00

CPC分类号： G06Q40/025 ,  G06Q20/24 ,  G06Q20/4014 ,  G06Q30/0185 ,  G10L17/00

摘要： In one embodiment, the invention provides a method, comprising: (a) maintaining a database of known fraudsters, wherein each fraudster has a voice signature and metadata associated therewith; (b) performing a screening operation to match a candidate with a fraudster in the database based on matching a voice signature and metadata for the candidate with a voice signature and metadata for the fraudster in the database.

摘要翻译： 在一个实施例中，本发明提供了一种方法，包括：（a）维护已知欺诈者的数据库，其中每个欺诈者具有与之相关联的语音签名和元数据; （b）基于将所述候选者的语音签名和元数据与数据库中的欺诈者的语音签名和元数据相匹配，执行筛选操作以使候选者与数据库中的欺诈者相匹配。

公开(公告)号：US20060248019A1

公开(公告)日：2006-11-02

申请号：US11404342

申请日：2006-04-14

申请人： Anthony Rajakumar

发明人： Anthony Rajakumar

IPC分类号： G06Q99/00

CPC分类号： G06Q20/4014 ,  G06Q20/24 ,  G06Q20/382

摘要： According to one aspect of the invention there is provided a method, comprising (a) maintaining a collection of voice signatures, at least a subset of which is organized to form a list of voice signatures, each belonging to a disqualified candidate; (b) obtaining a voice sample for a candidate; (c) comparing the voice sample with the voice signatures in the list; and (d) if the voice sample matches a signature in the list, then returning a status of disqualified for the candidate. According to another aspect of the invention there is provided a method, comprising receiving a request form a merchant to perform a fraud detection operation in connection with a credit card transaction by a consumer; responsive to the request, collecting a voice sample from the consumer; comparing the collected voice sample with voice signatures of known fraudsters; and notifying the merchant of a result of the comparing.

摘要翻译： 根据本发明的一个方面，提供了一种方法，包括：（a）保持语音签名的集合，其中至少一个子集被组织以形成语音签名列表，每个语音签名列表属于取消资格的候选者; （b）为候选人取得语音样本; （c）将语音样本与列表中的语音签名进行比较; 和（d）如果语音样本与列表中的签名相匹配，则返回候选人不符合资格的状态。 根据本发明的另一方面，提供了一种方法，包括从商家接收请求，以便与消费者进行信用卡交易相关的欺诈检测操作; 响应该请求，从消费者收集语音样本; 将收集到的语音样本与已知欺诈者的语音签名进行比较; 并通知商家比较结果。

公开(公告)号：US07724888B1

公开(公告)日：2010-05-25

申请号：US11167449

申请日：2005-06-27

申请人： Ryan J. Bush ,  Bertrand A. Damiba ,  Anthony Rajakumar

发明人： Ryan J. Bush ,  Bertrand A. Damiba ,  Anthony Rajakumar

IPC分类号： H04M7/00 ,  H04M3/00 ,  H04M5/00 ,  H04M1/64

CPC分类号： H04M3/4936

摘要： An automated method for determining user satisfaction with a call comprising (1) maintaining a count of the number of times a user was asked for input during the call (the “actual count”), (2) maintaining a count of the number of times a user should have been asked for input based on the dialog path the user traversed (the “ideal count”), and (3) associating no difference between the actual count and the ideal count with maximum user satisfaction and associating increasing differences between the counts with decreasing user satisfaction. In one embodiment, if the difference between the actual count and ideal count reaches a certain threshold, the call system changes the interaction with the user.

摘要翻译： 一种用于确定用户对呼叫对呼叫的呼叫的自动化方法，包括：（1）保持在呼叫期间用户被要求输入的次数的计数（“实际计数”），（2）保持次数的计数 应该根据用户所经过的对话路径（“理想计数”）询问用户的输入，以及（3）以最大的用户满意度将实际计数与理想计数之间的差值相关联，并且将计数之间的增加的差异相关联 用户满意度下降。 在一个实施例中，如果实际计数和理想计数之间的差达到一定阈值，则呼叫系统改变与用户的交互。

公开(公告)号：US08311826B2

公开(公告)日：2012-11-13

申请号：US13278067

申请日：2011-10-20

申请人： Anthony Rajakumar

发明人： Anthony Rajakumar

IPC分类号： G10L17/00 ,  G10L11/00 ,  G06Q99/00

CPC分类号： G06Q40/025 ,  G06Q20/24 ,  G06Q20/4014 ,  G06Q30/0185 ,  G10L17/00

摘要： In one embodiment, the invention provides a method, comprising: (a) maintaining a database of known fraudsters, wherein each fraudster has a voice signature and metadata associated therewith; (b) performing a screening operation to match a candidate with a fraudster in the database based on matching a voice signature and metadata for the candidate with a voice signature and metadata for the fraudster in the database.

摘要翻译： 在一个实施例中，本发明提供了一种方法，包括：（a）维护已知欺诈者的数据库，其中每个欺诈者具有与之相关联的语音签名和元数据; （b）基于将所述候选者的语音签名和元数据与数据库中的欺诈者的语音签名和元数据相匹配，执行筛选操作以使候选者与数据库中的欺诈者相匹配。

公开(公告)号：US20070280436A1

公开(公告)日：2007-12-06

申请号：US11754975

申请日：2007-05-29

申请人： Anthony Rajakumar

发明人： Anthony Rajakumar

IPC分类号： H04M1/64

CPC分类号： G06Q20/4014 ,  G06Q20/24 ,  G10L17/00

摘要： In one embodiment the invention provides a method, comprising: (a) obtaining an audio recording corresponding to a legal proceeding of interest; (b) extracting from the audio recording audio belonging to of the defendant of the legal proceeding; and (c) enrolling the extracted audio into a voiceprint database.

摘要翻译： 在一个实施例中，本发明提供了一种方法，包括：（a）获得与感兴趣的法律程序相对应的音频记录; （b）从属于法定诉讼程序的被告的音频录音中提取; 和（c）将提取的音频注册到声纹数据库中。

公开(公告)号：US20170339139A1

公开(公告)日：2017-11-23

申请号：US15587870

申请日：2017-05-05

申请人： Anthony Rajakumar

发明人： Anthony Rajakumar

IPC分类号： H04L29/06 ,  H04N21/4415 ,  H04N21/4627 ,  G06K9/00 ,  H04L29/12

CPC分类号： H04L63/0861 ,  G06K9/00899 ,  H04L61/1523 ,  H04L61/6022 ,  H04N21/41407 ,  H04N21/4415 ,  H04N21/4627

摘要： An automated process is disclosed for improving the functionality of computer systems and electronic commerce in user identity-proofing. Steps include verifying that a user who is electronically seeking identity proofing is on an electronic directory of persons eligible for such identity proofing; creating an attest list for the user that includes associates who can vouch for his or her identity; collecting a video or other data from the user; sending the video or data to the associates and asking them for a confirmation or a disavowal of the identity of the user; deriving a biometric from the video or data upon receiving the confirmation; and saving the biometric as an identify-proofed biometric.